© 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. 90884
    Prev
    Next
    INDEX
    Explanations

    medical contexts

    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
    ftagPool
    -0.81
    IsContent
    -0.77
    MessageOf
    -0.77
    GraphicsUnit
    -0.71
    adaptiveStyles
    -0.69
    hyrchwyd
    -0.67
    IsMutable
    -0.66
     Normdatei
    -0.64
    AnchorStyles
    -0.64
    uxxxx
    -0.63
    POSITIVE LOGITS
     reflective
    0.45
    [*
    0.42
    felizmente
    0.41
    ancourt
    0.41
    LikeLike
    0.40
     majority
    0.40
    ADR
    0.40
    icius
    0.39
     who
    0.39
    jsonp
    0.38
    Activations Density 0.009%

    No Known Activations