Assess feature importance in Keras for one-hot-encoded categorical features

An important aspect of tuning a model is assessing feature importance.

In Keras, how to assess the importance of a categorical feature which is one-hot encoded?

E.g. if a categorical feature is ice_cream_colour with a cardinality of 12 then I can assess the individual importances of ice_cream_colour_blue, ice_cream_colour_red, etc, but how to do it for the entire ice_cream_colour feature?

A naïve approach would be to sum all individual importances, but this assumes that the relationship between distinct feature importances is linear, which may not be the case.