© 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. 95415
    Prev
    Next
    INDEX
    Explanations

    Bond and/or de- prefix

    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
    Not in Any Lists

    No Comments

    Negative Logits
     daughter
    -0.96
     son
    -0.57
     grandson
    -0.55
     Tochter
    -0.50
     filha
    -0.49
     dochter
    -0.49
     hija
    -0.47
    児
    -0.45
     étrangères
    -0.43
     deschis
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.78
    usitis
    0.76
     Waray
    0.75
    andExpect
    0.73
     للاسماء
    0.72
    expandindo
    0.71
    =$?
    0.71
    例文帳に追加
    0.71
    mbals
    0.70
    )");
    0.70
    Activations Density 0.061%

    No Known Activations