© 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. 245
    Prev
    Next
    INDEX
    Explanations

    patterns and structures commonly associated with programming code or data representation

    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
     usual
    -0.48
     Regierungs
    -0.44
     Vorsitzende
    -0.41
     plain
    -0.40
     whole
    -0.40
     offiziellen
    -0.40
     Präsidenten
    -0.40
     separately
    -0.39
     typical
    -0.39
     allgemeinen
    -0.39
    POSITIVE LOGITS
     estekak
    0.75
    Obrázky
    0.74
    Datuak
    0.72
     BoxDecoration
    0.71
     betweenstory
    0.62
    ScopeManager
    0.61
     nakalista
    0.60
    WriteTagHelper
    0.58
    sendLogPayload
    0.56
    ViewImports
    0.56
    Activations Density 0.905%

    No Known Activations