© 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. 1-CLT-HP
    7. 14728
    Prev
    Next
    INDEX
    Explanations

    wide

    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
    complexType
    -0.65
    出版年
    -0.60
     maïs
    -0.60
     déri
    -0.60
     strto
    -0.57
    UrlResolution
    -0.56
     testemun
    -0.56
    ãe
    -0.56
    addCriterion
    -0.56
    ArrowToggle
    -0.56
    POSITIVE LOGITS
    Datuak
    0.52
    ville
    0.48
    Rohy
    0.47
    Geplaatst
    0.46
     selection
    0.46
     range
    0.43
     Unavailable
    0.43
    jstor
    0.42
    XM
    0.42
    نس
    0.42
    Activations Density 0.015%

    No Known Activations