© 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. 5-CLT-HP
    7. 5089
    Prev
    Next
    INDEX
    Explanations

    violations/failures

    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
     transférez
    -0.70
     @"/
    -0.65
    PreferredItem
    -0.59
     مشين
    -0.59
     ویکی‌پدیا
    -0.59
    vera
    -0.54
    ($__
    -0.53
    awtextra
    -0.53
     tàn
    -0.52
    migrationBuilder
    -0.51
    POSITIVE LOGITS
     contract
    0.63
     Contract
    0.54
     fiducia
    0.53
     facie
    0.52
     warranty
    0.50
    contract
    0.48
     fiduciary
    0.48
     kepercayaan
    0.47
    Contract
    0.47
     of
    0.47
    Activations Density 0.006%

    No Known Activations