© 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. 9682
    Prev
    Next
    INDEX
    Explanations

    hear

    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
     hearing
    -1.00
     heard
    -0.97
     hear
    -0.93
     hears
    -0.84
     Hearing
    -0.78
     HEARING
    -0.77
    hearing
    -0.77
    Heard
    -0.74
     Hear
    -0.73
    Hearing
    -0.73
    POSITIVE LOGITS
     Efq
    0.80
    maakt
    0.75
    expandindo
    0.73
     Theſe
    0.70
     reaſon
    0.70
     ſeveral
    0.69
    цездатний
    0.69
    yntaxException
    0.69
     étoit
    0.68
     juſt
    0.67
    Activations Density 0.009%

    No Known Activations