© 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. 71786
    Prev
    Next
    INDEX
    Explanations

    Introductory/descriptive texts

    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
    )•
    -0.40
    ']")
    -0.37
    ']").
    -0.35
    ())->
    -0.35
    chartInstance
    -0.33
    '])->
    -0.32
    ]").
    -0.31
     ());
    -0.30
    श्लेषण
    -0.30
     unary
    -0.30
    POSITIVE LOGITS
     About
    0.75
     ABOUT
    0.75
    About
    0.73
     Related
    0.72
     Disclaimer
    0.71
    ABOUT
    0.69
     If
    0.68
    Disclaimer
    0.68
     This
    0.66
     ویکی‌پدیای
    0.66
    Activations Density 0.235%

    No Known Activations