© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95081
    Prev
    Next
    INDEX
    Explanations

    amount

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.64
     présentés
    -0.54
     calda
    -0.52
     ficando
    -0.50
    ="#"><
    -0.49
     större
    -0.46
    getContentPane
    -0.45
    ⓧ
    -0.45
     polvere
    -0.44
     placés
    -0.43
    POSITIVE LOGITS
     विश्वसनीयता
    0.68
     wireType
    0.65
     ModelExpression
    0.64
    MLLoader
    0.63
     мәкал
    0.62
    rawDesc
    0.60
     للمعارف
    0.59
     detail
    0.57
     <=",
    0.57
    +#+
    0.57
    Activations Density 0.001%

    No Known Activations