© 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. 5-CLT-HP
    7. 90989
    Prev
    Next
    INDEX
    Explanations

    Jade

    np_max-act · 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
     kasarigan
    -0.73
    CloseOperation
    -0.61
     BeautifulSoup
    -0.59
    WindowConstants
    -0.57
    MessageTagHelper
    -0.57
     mourut
    -0.57
    లాలు
    -0.56
     aisladas
    -0.56
     مشين
    -0.55
     marinho
    -0.55
    POSITIVE LOGITS
    ite
    0.77
     typelib
    0.54
    ITE
    0.53
    нику
    0.49
    itu
    0.48
     nahilalakip
    0.48
    tu
    0.46
    iti
    0.45
     handleClick
    0.44
    ucky
    0.44
    Activations Density 0.001%

    No Known Activations