© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6061
    Prev
    Next
    INDEX
    Explanations

    Quantifiers and comparatives

    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
    Negative Logits
    AccessorTable
    -0.52
     дописавши
    -0.52
     ویکی‌پدیا
    -0.47
     Drapeau
    -0.46
     تانيه
    -0.43
     cốc
    -0.42
    DispatchToProps
    -0.42
     تضيفلها
    -0.42
    XmlRootElement
    -0.40
    Kedves
    -0.40
    POSITIVE LOGITS
    artments
    0.61
    IActionResult
    0.61
    клопе
    0.60
    TargetException
    0.59
    ircraft
    0.59
     ExecuteAsync
    0.57
    WriteLiteral
    0.57
    StateList
    0.57
     victims
    0.56
     IActionResult
    0.56
    Activations Density 0.003%

    No Known Activations