© 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. 78221
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    ymce
    -0.70
    CloseOperation
    -0.67
     الحره
    -0.66
    reportWebVitals
    -0.63
    NameInMap
    -0.63
    /%
    -0.62
     ratio
    -0.62
     /(\
    -0.61
     незавершена
    -0.59
     /(
    -0.57
    POSITIVE LOGITS
    __*/
    0.53
    thâu
    0.52
    хьтан
    0.51
     profondeur
    0.49
     المعيارى
    0.49
    typeof
    0.47
    UnifiedTopology
    0.47
     oldest
    0.44
    Ран
    0.43
     jspb
    0.43
    Activations Density 0.006%

    No Known Activations