© 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. 43445
    Prev
    Next
    INDEX
    Explanations

    disasters or sadness

    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
     tragedy
    -1.23
     tragedia
    -0.93
     Tragedy
    -0.90
     Disaster
    -0.83
     tragedies
    -0.83
     tragé
    -0.82
     disaster
    -0.80
     ")");
    -0.79
    trauma
    -0.78
     tragic
    -0.78
    POSITIVE LOGITS
    e
    0.80
    м
    0.54
    ever
    0.52
    ed
    0.52
    awtextra
    0.47
    a
    0.47
    o
    0.46
    eff
    0.46
     strike
    0.44
    maker
    0.44
    Activations Density 0.158%

    No Known Activations