© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 45489 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45489

INDEX

Explanations

disguise

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ar

-0.62

di

-0.59

 Dress

-0.50

 accessible

-0.48

sider

-0.48

to

-0.48

 esta

-0.47

or

-0.47

resses

-0.47

ein

-0.46

POSITIVE LOGITS

 myſelf

1.29

 raiſ

1.26

 Monfieur

1.23

 Theſe

1.19

 ſeveral

1.16

 itſelf

1.16

 uſed

1.15

 againſt

1.14

 ſta

1.13

Efq

1.13

Activations Density 0.356%

No Known Activations