© 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. 94325
    Prev
    Next
    INDEX
    Explanations

    approximation

    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
    -1.34
     hear
    -1.20
     hears
    -1.11
    hearing
    -0.96
     pretty
    -0.93
    Pretty
    -0.92
     ganska
    -0.91
     dentaire
    -0.88
     heard
    -0.86
    Hearing
    -0.86
    POSITIVE LOGITS
     the
    0.68
     <",
    0.60
    cess
    0.59
    gez
    0.58
    SourceChecksum
    0.57
     “
    0.56
     human
    0.56
    le
    0.55
    ness
    0.54
    ul
    0.54
    Activations Density 0.617%

    No Known Activations