© 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. 4718
    Prev
    Next
    INDEX
    Explanations

    code and technical descriptions

    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
    seamnă
    -0.61
     điện
    -0.42
     κό
    -0.41
     рода
    -0.40
     ام
    -0.39
     a
    -0.38
    氨
    -0.38
    tación
    -0.37
     "
    -0.37
    تل
    -0.37
    POSITIVE LOGITS
    WireFormatLite
    0.98
    principalColumn
    0.95
    InjectAttribute
    0.94
    GraphicsUnit
    0.94
     مشين
    0.91
    TypedDataSet
    0.90
    UnusedPrivate
    0.90
    WriteBarrier
    0.89
     समीक्षाएं
    0.87
    sizeCache
    0.85
    Activations Density 0.008%

    No Known Activations