© 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 · 45620 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45620

INDEX

Explanations

believed

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

 believed

-1.00

 meant

-0.92

 felt

-0.91

 thought

-0.90

was

-0.74

 proved

-0.74

-0.70

 seemed

-0.69

is

-0.64

-0.64

POSITIVE LOGITS

 Monfieur

1.12

 Anſ

1.09

 myſelf

1.05

Efq

1.01

 itſelf

0.99

^(@)

0.98

 iſt

0.96

 Roskov

0.95

 Theſe

0.94

 ſind

0.94

Activations Density 0.323%

No Known Activations