© 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. 72624
    Prev
    Next
    INDEX
    Explanations

    Jargon and computer code

    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
     muri
    -0.71
     Alve
    -0.70
     ModelExpression
    -0.70
    phinx
    -0.69
    IsMutable
    -0.69
     kasarigan
    -0.68
    MemoryWarning
    -0.67
    AttributeSet
    -0.66
     AppModule
    -0.66
     >=",
    -0.66
    POSITIVE LOGITS
    Chham
    0.40
    Portale
    0.40
    VersionUID
    0.39
    extrême
    0.39
     serious
    0.38
    jsxFileName
    0.38
    rouvez
    0.36
    HomeAsUpEnabled
    0.36
    زارش
    0.36
     folle
    0.36
    Activations Density 0.000%

    No Known Activations