© 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. 5-CLT-HP
    7. 4567
    Prev
    Next
    INDEX
    Explanations

    Medical 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
     tromper
    -0.55
     felipe
    -0.49
     Knoblauch
    -0.47
     culturelles
    -0.46
    pop
    -0.46
    MockBean
    -0.45
     démocr
    -0.45
    tomb
    -0.45
     ouvriers
    -0.45
    auk
    -0.45
    POSITIVE LOGITS
    :✨
    0.69
    bootstrapcdn
    0.65
     للاسماء
    0.64
    MigrationBuilder
    0.57
     okuyayım
    0.56
    IContainer
    0.56
    )))));
    0.55
    providedIn
    0.55
    URUS
    0.53
    ":[{
    0.53
    Activations Density 0.007%

    No Known Activations