© 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. 71463
    Prev
    Next
    INDEX
    Explanations

    programming code/documentation

    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
     lower
    -0.81
     poorer
    -0.79
     weaker
    -0.78
     lesser
    -0.77
    lower
    -0.77
     Lesser
    -0.77
     inferior
    -0.73
     higher
    -0.71
    higher
    -0.70
     inférieur
    -0.70
    POSITIVE LOGITS
    protoimpl
    0.60
    ьаж
    0.54
    CROSSTALK
    0.53
    XmlEnum
    0.51
    AnchorStyles
    0.49
     ویکی‌پدیا
    0.46
    jooq
    0.46
     GENERATED
    0.46
    ftagPool
    0.46
     CYTHON
    0.44
    Activations Density 0.007%

    No Known Activations