© 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. 0-CLT-HP
    7. 94792
    Prev
    Next
    INDEX
    Explanations

    pneumonia

    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
     GenerationType
    -0.70
     pneumonia
    -0.65
     autobiography
    -0.61
     لينك
    -0.61
    ificantly
    -0.61
     Etr
    -0.60
    ly
    -0.59
    🏼
    -0.58
     autorytatywna
    -0.58
    TestingModule
    -0.57
    POSITIVE LOGITS
    WireFormatLite
    0.59
    الإنجليزية
    0.56
    winston
    0.50
    ViewFeatures
    0.49
    %")
    0.47
    %");
    0.47
    astify
    0.45
    "+
    0.44
    vitt
    0.44
    mıştır
    0.44
    Activations Density 0.168%

    No Known Activations