© 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. 5-CLT-HP
    7. 6320
    Prev
    Next
    INDEX
    Explanations

    of

    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
     quedado
    -0.50
     gehalten
    -0.49
    rodalom
    -0.48
    μφωνα
    -0.46
    มาะ
    -0.45
    chalten
    -0.44
    gorithm
    -0.44
     jugé
    -0.44
    えています
    -0.44
    bezpiecz
    -0.44
    POSITIVE LOGITS
     how
    0.83
    Rüyada
    0.73
    :✨
    0.69
     <=",
    0.69
     what
    0.65
     a
    0.64
     why
    0.64
    хьтан
    0.59
     something
    0.59
     an
    0.58
    Activations Density 0.002%

    No Known Activations