© 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. 8753
    Prev
    Next
    INDEX
    Explanations

    medical trauma

    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
    Portail
    -0.66
    writerow
    -0.65
     **)
    -0.61
    :])
    -0.61
     CURIAM
    -0.60
    PhysRev
    -0.57
     sinner
    -0.57
    ﴿
    -0.56
    tagext
    -0.56
     Baz
    -0.56
    POSITIVE LOGITS
     متعلقه
    0.56
    amını
    0.50
     Bloom
    0.44
     Kitch
    0.43
    cestershire
    0.43
    InsertCommand
    0.42
     joindre
    0.42
    ahashi
    0.41
     kuiten
    0.41
    neapolis
    0.41
    Activations Density 0.068%

    No Known Activations