© 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. 42748
    Prev
    Next
    INDEX
    Explanations

    holes or permissions

    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
     holes
    -1.63
     Holes
    -1.36
     permission
    -1.14
    Holes
    -1.03
    holes
    -1.02
     privilege
    -0.92
     Permission
    -0.84
     hole
    -0.82
    permission
    -0.82
     agujeros
    -0.82
    POSITIVE LOGITS
    LayoutStyle
    0.56
    yorsunuz
    0.53
    codehaus
    0.50
     vulgaires
    0.50
    setOnAction
    0.48
     oyn
    0.48
    UseVisualStyle
    0.47
    Politik
    0.47
    ității
    0.47
    fjspx
    0.47
    Activations Density 1.741%

    No Known Activations