© 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. 20-CLT-HP
    7. 71500
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · 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
     مرئيه
    -0.71
     InputDecoration
    -0.65
     vuitton
    -0.61
    GEBURTSDATUM
    -0.60
    Autoritní
    -0.59
     Terrier
    -0.57
    hoodie
    -0.56
    SÍ
    -0.56
    tomos
    -0.56
    iseries
    -0.55
    POSITIVE LOGITS
     South
    0.59
     Southeast
    0.57
     East
    0.54
    UALA
    0.51
     Fort
    0.51
    South
    0.50
    ⓘ
    0.49
    East
    0.49
     Ar
    0.48
    la
    0.45
    Activations Density 0.002%

    No Known Activations