INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
56
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
elements related to formatting or structure in text
New Auto-Interp
Negative Logits
)
-0.35
-0.35
Literatur
-0.33
Request
-0.31
andExpect
-0.31
isième
-0.31
-0.31
))=
-0.30
request
-0.30
newArrayList
-0.29
POSITIVE LOGITS
betweenstory
0.68
########.
0.66
ंदीखरीदारी
0.64
Administrativna
0.62
raiſ
0.60
ſta
0.59
queſta
0.59
Taktlose
0.59
purpoſe
0.57
nonUne
0.57
Activations Density 1.962%