INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
74
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
words related to positive emotions and enjoyable experiences
New Auto-Interp
Negative Logits
WriteTagHelper
-0.51
bootstrapcdn
-0.51
Personendaten
-0.50
theoretically
-0.50
Jazeera
-0.49
sistors
-0.49
tyimages
-0.47
zeera
-0.46
Sheet
-0.46
Sheets
-0.46
POSITIVE LOGITS
enjoyment
0.63
enjoy
0.58
joyful
0.57
enjoy
0.56
Enjoy
0.56
Enjoy
0.56
enjoyable
0.56
joy
0.52
gioia
0.51
enjoyed
0.50
Activations Density 0.001%