© 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. 71360
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
    EndInit
    -0.88
    expandindo
    -0.85
    ьаж
    -0.77
     gynhyrchwyd
    -0.74
    पया
    -0.70
    protoimpl
    -0.70
    SourceChecksum
    -0.70
    GEBURTSDATUM
    -0.69
     <=",
    -0.69
     समीक्षाओं
    -0.69
    POSITIVE LOGITS
     clearly
    0.84
     straight
    0.78
    clearly
    0.57
     things
    0.56
     STRA
    0.54
     plainly
    0.51
    TestBed
    0.51
    drawRect
    0.50
    Things
    0.49
     Clearly
    0.48
    Activations Density 0.000%

    No Known Activations