© 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. 8641
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
    GetAxis
    -0.59
    DoubleQuotes
    -0.54
    printLine
    -0.54
     الحره
    -0.52
    ucket
    -0.48
    RunAsync
    -0.48
     fieldNum
    -0.48
    +#+#
    -0.48
    bootstrapcdn
    -0.47
    ollectionView
    -0.45
    POSITIVE LOGITS
     Efq
    0.79
     avoient
    0.73
     perfons
    0.68
     poffe
    0.67
     houſe
    0.66
     quæ
    0.63
     cdti
    0.63
     Audiodateien
    0.61
     Houſe
    0.59
     étoit
    0.58
    Activations Density 0.082%

    No Known Activations