INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
40.25
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
specific mathematical symbols and formatting, particularly relating to equations and expressions
New Auto-Interp
Negative Logits
)
-0.33
umane
-0.31
-0.30
adulte
-0.29
person
-0.29
ưở
-0.29
probablement
-0.28
terbang
-0.28
בש
-0.28
wiedzy
-0.27
POSITIVE LOGITS
autorytatywna
0.87
nakalista
0.82
تضيفلها
0.69
setVerticalGroup
0.68
bibfield
0.68
rrggbb
0.67
évaluateur
0.64
transQ
0.63
WriteAttribute
0.63
BufferException
0.63
Activations Density 0.591%