© 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. 1-CLT-HP
    7. 10244
    Prev
    Next
    INDEX
    Explanations

    import

    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
     виправивши
    -1.00
    jsxFileName
    -0.91
    tagHelperRunner
    -0.91
     autorytatywna
    -0.90
     ProtoMessage
    -0.83
    ANDUM
    -0.76
    RTLD
    -0.73
    IsMutable
    -0.72
    Autoritní
    -0.72
    elemField
    -0.71
    POSITIVE LOGITS
    I
    0.52
    getStatus
    0.46
     mesmos
    0.44
    a
    0.44
     mesma
    0.43
    Phaser
    0.42
    ”
    0.42
     pertinente
    0.41
    </
    0.41
    }}/>
    0.41
    Activations Density 0.351%

    No Known Activations