© 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. 71292
    Prev
    Next
    INDEX
    Explanations

    research code products

    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
     للاسماء
    -0.73
     aDecoder
    -0.73
     propOrder
    -0.68
    IUrlHelper
    -0.65
    Chham
    -0.63
    featureID
    -0.63
    HasAnnotation
    -0.62
    ագրություններ
    -0.61
     referenties
    -0.60
     initComponents
    -0.60
    POSITIVE LOGITS
    IsContent
    0.47
     состав
    0.46
    uc
    0.46
     Millennium
    0.45
    delsen
    0.44
     Development
    0.44
    webElementXpaths
    0.44
     nicio
    0.44
    push
    0.43
    !("{
    0.43
    Activations Density 0.000%

    No Known Activations