© 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. 94525
    Prev
    Next
    INDEX
    Explanations

    important

    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
     an
    -0.75
     a
    -0.65
     those
    -0.62
     to
    -0.60
     belangrij
    -0.59
    scripts
    -0.56
    alties
    -0.56
     courses
    -0.55
     wrappers
    -0.55
     bonté
    -0.54
    POSITIVE LOGITS
     épaules
    0.62
     prochaines
    0.60
    HtmlAttribute
    0.57
    出版年
    0.57
     lèvres
    0.56
     image
    0.54
     navires
    0.54
     feature
    0.52
     beaker
    0.52
     vaisseaux
    0.52
    Activations Density 0.053%

    No Known Activations