© 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. 103
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols, particularly related to equations and expressions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Inscrivez
    -0.56
    berdayakan
    -0.54
    httphttps
    -0.50
     Económica
    -0.44
    ßerdem
    -0.43
     gethan
    -0.43
     Könige
    -0.43
     الحره
    -0.42
    AddTagHelper
    -0.42
     gewiß
    -0.40
    POSITIVE LOGITS
    ⓧ
    0.73
    хьтан
    0.60
    (&:
    0.57
    yx
    0.57
    nof
    0.56
     Montal
    0.56
     Vanden
    0.56
    poxy
    0.54
     Dc
    0.54
    Jerry
    0.54
    Activations Density 11.500%

    No Known Activations