INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
84
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
references to punctuation and symbolic formatting
New Auto-Interp
Negative Logits
Virt
-0.37
Everybody
-0.37
magnet
-0.37
vir
-0.37
biggest
-0.37
Життєпис
-0.36
grond
-0.36
一大
-0.36
foobar
-0.36
pexpr
-0.35
POSITIVE LOGITS
Administrativna
0.74
autorytatywna
0.60
Taktlose
0.60
PerformLayout
0.56
Chham
0.55
betweenstory
0.52
Билгалдахарш
0.50
ValueStyle
0.50
Tikang
0.49
Хьажоргаш
0.49
Activations Density 0.369%