© 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. 15774
    Prev
    Next
    INDEX
    Explanations

    medical/scientific imaging

    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
     Waray
    -0.64
    onin
    -0.57
    protoc
    -0.53
    ậc
    -0.50
    EndContext
    -0.48
    ArgsConstructor
    -0.47
     InputDecoration
    -0.47
     uș
    -0.47
     primiti
    -0.47
     noqa
    -0.47
    POSITIVE LOGITS
    itively
    0.54
    ylem
    0.52
    Hrsg
    0.52
    ativistic
    0.50
    isteria
    0.49
    ANEOUS
    0.49
    ETIME
    0.49
     unknownFields
    0.49
    ulton
    0.48
    sieke
    0.48
    Activations Density 0.023%

    No Known Activations