© 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. 1-CLT-HP
    7. 8736
    Prev
    Next
    INDEX
    Explanations

    In/On

    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
     the
    -0.76
     an
    -0.73
     a
    -0.71
     this
    -0.69
     last
    -0.59
     each
    -0.57
     past
    -0.57
     exactly
    -0.54
     future
    -0.54
     our
    -0.54
    POSITIVE LOGITS
    Hentet
    0.58
    kuuta
    0.50
    tableFuture
    0.50
     Infórmanos
    0.47
    blende
    0.46
    kadang
    0.45
    Referanser
    0.45
     prohibido
    0.44
     revés
    0.44
    šanai
    0.44
    Activations Density 0.034%

    No Known Activations