© 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. 71492
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text snippets

    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
     autorytatywna
    -0.85
     تضيفلها
    -0.85
     <=",
    -0.69
    Datuak
    -0.66
     sẻ
    -0.66
    
    -0.66
    ✨:
    -0.63
    CodeAttribute
    -0.63
     vagu
    -0.62
    expandindo
    -0.59
    POSITIVE LOGITS
     a
    0.74
     game
    0.65
    game
    0.64
     paradigm
    0.56
     ground
    0.51
     an
    0.50
     radical
    0.49
     angin
    0.49
    tre
    0.48
     quantum
    0.48
    Activations Density 0.000%

    No Known Activations