© 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. 0-CLT-HP
    7. 43154
    Prev
    Next
    INDEX
    Explanations

    GRAPH_NAME_H

    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
     themselves
    -0.55
    himself
    -0.53
     members
    -0.51
     MMMM
    -0.50
     Himself
    -0.50
    wachung
    -0.50
     وسلم
    -0.50
     himself
    -0.49
    ellingham
    -0.47
     zichzelf
    -0.47
    POSITIVE LOGITS
    UserScript
    0.87
    mybatisplus
    0.65
     MenuView
    0.65
     Wikimedijinoj
    0.62
     ModelExpression
    0.62
    QMetaType
    0.59
    HasAnnotation
    0.57
    Deja
    0.56
    SharedDtor
    0.56
     decimal
    0.55
    Activations Density 1.809%

    No Known Activations