© 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. 71533
    Prev
    Next
    INDEX
    Explanations

    Code/Foreign language/Medical

    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
    /******/
    -0.60
    uggest
    -0.59
     jScrollPane
    -0.56
    viewpager
    -0.54
    igre
    -0.48
     Paglinawan
    -0.47
    DllImport
    -0.47
    ladesh
    -0.46
     schlagen
    -0.46
     cage
    -0.46
    POSITIVE LOGITS
    
    0.75
     الحره
    0.68
    aarrggbb
    0.61
    atosis
    0.59
    WithIOException
    0.57
     }}"></
    0.56
    atal
    0.53
    ental
    0.52
    GEBURTSDATUM
    0.52
    ẫ
    0.52
    Activations Density 0.023%

    No Known Activations