© 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. 421
    Prev
    Next
    INDEX
    Explanations

    concepts related to scientific and mathematical analysis in biological and financial 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
     resourceCulture
    -0.60
     BorderSide
    -0.57
     Houſe
    -0.56
    tease
    -0.54
    征詢我
    -0.53
     createSprite
    -0.53
    Tikang
    -0.52
    parsedMessage
    -0.52
    posedge
    -0.52
     encre
    -0.50
    POSITIVE LOGITS
    physical
    0.54
    physics
    0.52
    mathematical
    0.49
     physical
    0.47
    Phys
    0.47
    phys
    0.46
    engineering
    0.45
    Physical
    0.45
    mechanical
    0.44
    scientific
    0.44
    Activations Density 5.109%

    No Known Activations