© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95768
    Prev
    Next
    INDEX
    Explanations

    kne

    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
    Negative Logits
     fall
    -1.32
     Fall
    -0.93
    fall
    -0.88
     FALL
    -0.79
     fallen
    -0.77
    a
    -0.77
     spring
    -0.73
    Fall
    -0.73
    o
    -0.72
    kno
    -0.71
    POSITIVE LOGITS
     Efq
    0.75
     Majefty
    0.74
    EndGlobalSection
    0.73
     myſelf
    0.71
    :✨
    0.69
     poffible
    0.69
    WebServlet
    0.68
     picioare
    0.68
     שוליים
    0.68
     Shakspeare
    0.67
    Activations Density 1.818%

    No Known Activations