© 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. 94680
    Prev
    Next
    INDEX
    Explanations

    some

    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
     enzyme
    -0.53
    GraphicsUnit
    -0.51
     anthropogenic
    -0.49
     immunological
    -0.46
     arrhyth
    -0.46
     overexpression
    -0.45
     enz
    -0.45
     compounds
    -0.44
     enzymes
    -0.43
     myeloma
    -0.43
    POSITIVE LOGITS
     more
    0.83
     bezeichneter
    0.78
     typelib
    0.71
     snippetHide
    0.69
    Становништво
    0.66
    Билгалдахарш
    0.65
    likation
    0.65
    новниш
    0.65
     More
    0.64
    eabouts
    0.64
    Activations Density 0.044%

    No Known Activations