© 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. 5-CLT-HP
    7. 97990
    Prev
    Next
    INDEX
    Explanations

    ze

    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
    testens
    -0.56
     Lég
    -0.55
     Serap
    -0.52
    })));
    -0.50
     jScrollPane
    -0.49
     Drapeau
    -0.49
    FDRE
    -0.48
    StructEnd
    -0.47
     Three
    -0.47
     Ire
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.72
    :✨
    0.70
     незавершена
    0.65
    mybatisplus
    0.62
    uxxxx
    0.59
    InitVars
    0.56
     للاسماء
    0.56
    يديا
    0.55
    Rüyada
    0.54
     ویکی‌پدیا
    0.53
    Activations Density 0.000%

    No Known Activations