© 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. 95352
    Prev
    Next
    INDEX
    Explanations

    scientific/medical abstracts

    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
    io
    -1.02
    ios
    -0.85
    IO
    -0.79
    IOS
    -0.65
     io
    -0.63
     IO
    -0.56
    iom
    -0.56
    iot
    -0.55
    iots
    -0.54
    iosi
    -0.53
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    AnchorStyles
    0.76
     greateſt
    0.68
     Diſ
    0.67
     ſtre
    0.67
     Reſ
    0.67
     MainAxisSize
    0.67
    miyorum
    0.66
    الإنجليزية
    0.65
    出版年
    0.65
    Activations Density 0.272%

    No Known Activations