© 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. 95685
    Prev
    Next
    INDEX
    Explanations

    we

    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
     Itself
    -0.70
    akah
    -0.63
     itself
    -0.57
     its
    -0.57
     ils
    -0.56
     it
    -0.56
     we
    -0.56
     they
    -0.55
     our
    -0.54
     Continues
    -0.53
    POSITIVE LOGITS
    '
    0.99
    ’
    0.88
     are
    0.71
     will
    0.69
     can
    0.68
    <bos>
    0.64
    rrggbb
    0.63
     may
    0.63
     appreciate
    0.63
    Demografia
    0.62
    Activations Density 0.046%

    No Known Activations