© 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. 10500
    Prev
    Next
    INDEX
    Explanations

    abuse

    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
    ב
    -0.78
     resourceCulture
    -0.69
    ggle
    -0.63
    IALES
    -0.57
    #+#
    -0.57
    jsxFileName
    -0.57
    DockStyle
    -0.56
    ίζ
    -0.54
     accessToken
    -0.54
     Inflate
    -0.54
    POSITIVE LOGITS
     disambiguazione
    0.66
    ChromeDriver
    0.65
    曖昧さ回避
    0.52
     propOrder
    0.51
    DeleteBehavior
    0.50
    SharedCtor
    0.50
     cref
    0.49
    ClientSize
    0.47
     initComponents
    0.47
    toso
    0.47
    Activations Density 0.034%

    No Known Activations