© 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. 6056
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Iné
    -0.56
    Последние
    -0.49
    elemField
    -0.49
    preduce
    -0.49
     in
    -0.48
    zeria
    -0.46
    在一
    -0.46
     contribute
    -0.45
    nemouth
    -0.45
     година
    -0.45
    POSITIVE LOGITS
     of
    1.52
    ของ
    0.75
     của
    0.75
    of
    0.74
     της
    0.60
     ofthe
    0.59
    ofthe
    0.58
     how
    0.57
    LookAnd
    0.57
    how
    0.56
    Activations Density 0.006%

    No Known Activations