© 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. 78004
    Prev
    Next
    INDEX
    Explanations

    intestinal

    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
     мәкал
    -0.88
    AnchorStyles
    -0.78
     للمعارف
    -0.74
     فريبيس
    -0.71
     Waz
    -0.68
    Autoritní
    -0.68
     الدولى
    -0.67
    RectangleBorder
    -0.66
    تقاوى
    -0.66
     transfieras
    -0.65
    POSITIVE LOGITS
    aba
    0.41
    (_.
    0.40
    sprechend
    0.38
     McMillan
    0.37
    ditor
    0.36
    )(((
    0.35
     Empieza
    0.35
     thường
    0.35
    )((
    0.35
     onData
    0.34
    Activations Density 0.001%

    No Known Activations