© 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. 1-CLT-HP
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    pathology

    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
     Pathology
    -1.21
     pathology
    -1.19
     Pathol
    -0.89
     pathologies
    -0.73
     pathological
    -0.68
     pathologist
    -0.62
    patho
    -0.61
    Patho
    -0.60
     vocational
    -0.54
    isela
    -0.52
    POSITIVE LOGITS
    Datuak
    0.69
     snippetHide
    0.68
    MigrationBuilder
    0.65
     समीक्षाओं
    0.63
    handleRequest
    0.63
     CreateTagHelper
    0.60
    IntoConstraints
    0.60
    \{\\
    0.59
    Geplaatst
    0.59
    DoubleQuotes
    0.59
    Activations Density 0.067%

    No Known Activations