© 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 · 45581 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45581

INDEX

Explanations

transform

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

edo

-0.43

 rato

-0.42

лё

-0.39

legung

-0.38

 corte

-0.38

 serie

-0.37

 poter

-0.37

ebel

-0.37

въ

-0.37

up

-0.36

POSITIVE LOGITS

 myſelf

0.98

 Reſ

0.96

 itſelf

0.96

 Monfieur

0.95

 Houſe

0.90

 AppColors

0.89

 Anſ

0.85

Eſ

0.85

 ―――――

0.84

 Majefty

0.82

Activations Density 1.113%

No Known Activations