INDEX

Model

gemma-2-9b-it

Layer #

Steering Hook

blocks.20.hook_resid_pre

Steering Strength

Uploader

bot-neuronpedia

Created At

2/15/2025 1:06:43 AM

Raw Vector

Actions

Explanations

instances of high-impact words or phrases that suggest importance or classification in contexts like rules, procedures, or significant events

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

pyvene/gemma-reft-r1-9b-it-res/l20

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 météo

-0.34

ėte

-0.32

 traditionally

-0.31

Historically

-0.31

 nawr

-0.31

 ekor

-0.31

-0.30

 terjun

-0.30

 historically

-0.29

ząd

-0.29

POSITIVE LOGITS

 noDo

0.66

webElementXpaths

0.61

Manbalar

0.59

ſelf

0.57

 AssemblyCompany

0.55

 purpoſe

0.55

Хьажоргаш

0.54

ContentAlignment

0.54

 CanadaChoose

0.54

fromnode

0.53

Activations Density 1.069%

instances of high-impact words or phrases that suggest importance or classification in contexts like rules, procedures, or significant events

No Comments

No Known Activations