© 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. 42946
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     المعرف
    -0.71
    RegressionTest
    -0.67
     Autorizaciones
    -0.67
     nonUne
    -0.66
     виправивши
    -0.65
     Auteur
    -0.65
     Exacts
    -0.65
    ftagPool
    -0.63
    клопе
    -0.62
    nezeu
    -0.62
    POSITIVE LOGITS
    vis
    0.38
    sufficient
    0.35
     متعلقه
    0.35
    inst
    0.34
    <i>
    0.33
    flow
    0.33
    CDN
    0.33
     Moscú
    0.32
     مرئيه
    0.32
    UARY
    0.32
    Activations Density 0.640%

    No Known Activations