© 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. 4-CLT-HP
    7. 3369
    Prev
    Next
    INDEX
    Explanations

    phone number

    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
    featureID
    -0.61
    Rujuakan
    -0.60
    :✨
    -0.57
     незавершена
    -0.57
     الرياضيه
    -0.56
    ेशा
    -0.56
    Legenda
    -0.53
    EndContext
    -0.53
    LayoutStyle
    -0.52
    ButterKnife
    -0.52
    POSITIVE LOGITS
     bestaan
    0.47
    })));
    0.46
    AccessorTable
    0.44
    StreetMap
    0.44
    hadas
    0.43
    cimento
    0.43
    hombo
    0.43
     Fati
    0.43
    ochond
    0.42
    artige
    0.41
    Activations Density 0.001%

    No Known Activations