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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73037
    Prev
    Next
    INDEX
    Explanations

    Formal/Technical language

    np_max-act-logits · 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
    ⓧ
    -0.97
     utafitiHapana
    -0.84
    :+:
    -0.82
     ویکی‌پدیا
    -0.81
     wireType
    -0.78
    tvguidetime
    -0.77
    rungsseite
    -0.73
    Spoljašnje
    -0.71
    ########.
    -0.69
     للاسماء
    -0.69
    POSITIVE LOGITS
     parent
    0.44
    RotationOrder
    0.44
     onData
    0.43
     carrying
    0.42
     carried
    0.42
     Breaking
    0.40
    carried
    0.40
    parent
    0.40
     BREAKING
    0.40
    Parent
    0.39
    Activations Density 0.000%

    No Known Activations