© 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. 1-CLT-HP
    7. 8638
    Prev
    Next
    INDEX
    Explanations

    polka

    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
    ly
    -0.51
     Vaux
    -0.44
    throw
    -0.44
    GetObject
    -0.43
     Adieu
    -0.42
    extend
    -0.42
    ous
    -0.42
    vece
    -0.42
    minds
    -0.42
    nex
    -0.42
    POSITIVE LOGITS
    Geplaatst
    0.69
     alimentaires
    0.64
    resave
    0.64
     typelib
    0.59
    sizeCache
    0.59
    writeField
    0.59
    fromCharCode
    0.57
     termica
    0.56
     ویکی‌پدی
    0.56
     bekas
    0.56
    Activations Density 0.053%

    No Known Activations