© 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. 322
    Prev
    Next
    INDEX
    Explanations

    sequences relating to scientific and technical terminology, particularly in biological and engineering contexts

    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
    TagMode
    -0.52
    IntoConstraints
    -0.48
     propOrder
    -0.46
    writerow
    -0.42
    endpush
    -0.42
    يكب
    -0.39
     HFILL
    -0.37
    variates
    -0.36
    genodigd
    -0.36
     DbContext
    -0.35
    POSITIVE LOGITS
    skrift
    0.47
     للاسماء
    0.42
    IGraphics
    0.42
     conmigo
    0.41
    contentLoaded
    0.40
    Pow
    0.39
     espes
    0.39
     postIndex
    0.39
    Heb
    0.39
    orak
    0.39
    Activations Density 12.285%

    No Known Activations