© 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. 10198
    Prev
    Next
    INDEX
    Explanations

    Medical/surgical procedures and cancer

    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
    estat
    -0.47
     sila
    -0.46
    tad
    -0.46
    idase
    -0.46
     fog
    -0.44
    azz
    -0.43
    bergen
    -0.42
    Organisateur
    -0.42
     inv
    -0.42
    ginate
    -0.41
    POSITIVE LOGITS
    WithIOException
    0.74
    WebVitals
    0.72
     незавершена
    0.70
     normaux
    0.68
     ſeveral
    0.67
    interopRequire
    0.67
    felves
    0.61
     considérons
    0.60
     appunto
    0.60
     يتيمه
    0.60
    Activations Density 0.010%

    No Known Activations