INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
72
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
references and citations in academic writing
New Auto-Interp
Negative Logits
⎨
-0.46
Audiodateien
-0.40
bewerken
-0.36
énéral
-0.35
realy
-0.35
Likely
-0.33
barata
-0.33
sistors
-0.33
WriteTagHelper
-0.33
|}
-0.33
POSITIVE LOGITS
Хьажоргаш
0.63
fromnode
0.61
Chham
0.52
references
0.52
setVerticalGroup
0.51
Autoritní
0.50
autorytatywna
0.49
Administrativna
0.49
referenced
0.48
msgTypes
0.47
Activations Density 2.939%