© 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. 1-CLT-HP
    7. 9479
    Prev
    Next
    INDEX
    Explanations

    medical/biological terms

    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
    jean
    -0.82
    levance
    -0.71
     незавершена
    -0.70
    expandindo
    -0.61
     capricious
    -0.61
     Derivation
    -0.61
     derivation
    -0.59
    Derivation
    -0.59
     caprice
    -0.59
     auffi
    -0.59
    POSITIVE LOGITS
    ed
    0.62
    DOCTYPE
    0.52
     הר
    0.48
    BorderSize
    0.47
    quels
    0.47
    epam
    0.47
    ikal
    0.46
     assumed
    0.45
    /******/
    0.44
    assumed
    0.44
    Activations Density 0.024%

    No Known Activations