© 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. 300
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related concepts in documentation or programming texts

    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
    AddTagHelper
    -0.88
     CreateTagHelper
    -0.85
    GEBURTSDATUM
    -0.82
     AssemblyTitle
    -0.74
    Autoritní
    -0.74
     ModelExpression
    -0.74
    RenderAtEndOf
    -0.73
     autorytatywna
    -0.71
    TagMode
    -0.70
    KURZBESCHREIBUNG
    -0.69
    POSITIVE LOGITS
    .../
    0.36
     uLocal
    0.36
    木
    0.34
    RAE
    0.33
    aaron
    0.33
    rold
    0.32
    ㉨
    0.32
    【
    0.32
    太
    0.32
    NP
    0.31
    Activations Density 45.323%

    No Known Activations