© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 45277 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
45277

INDEX

Explanations

wasn't

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

 wasn

-0.70

men

-0.56

 weren

-0.54

 wasnt

-0.50

liğ

-0.49

hal

-0.48

was

-0.47

-0.45

headers

-0.45

ster

-0.44

POSITIVE LOGITS

]--;

1.01

 iſt

0.76

 Jefus

0.76

 Theſe

0.74

 betweenstory

0.72

 ſind

0.71

^(@)

0.70

 raiſ

0.68

 useRef

0.68

RegistryLite

0.68

Activations Density 0.255%

No Known Activations