© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 283
    Prev
    Next
    INDEX
    Explanations

    structural elements or patterns in data syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.93
    parsedMessage
    -0.83
    IUrlHelper
    -0.78
    MLLoader
    -0.77
     transfieras
    -0.77
    出版年
    -0.74
    LookAnd
    -0.71
     kaarangay
    -0.68
     ویکی‌پدی
    -0.66
    styleType
    -0.66
    POSITIVE LOGITS
     bolsillos
    0.47
     delegación
    0.47
     amado
    0.46
     cárcel
    0.44
     pihaknya
    0.44
     excepción
    0.44
     informática
    0.44
     correspondiente
    0.44
     vegetación
    0.43
     orilla
    0.43
    Activations Density 2.939%

    No Known Activations