© 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. 34
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical notation or symbols

    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
    tonode
    -0.40
     Réponses
    -0.39
    NamedQueries
    -0.34
    AnchorTagHelper
    -0.32
    AddHtmlAttribute
    -0.32
     and
    -0.28
    evaluated
    -0.28
    SourceChecksum
    -0.28
     વ
    -0.28
    WillAppear
    -0.27
    POSITIVE LOGITS
    /**
    0.76
    IsContent
    0.75
    iſen
    0.72
    niſſe
    0.71
    JAKARTA
    0.67
    ſchaft
    0.66
     ſei
    0.66
    ſelben
    0.66
     autorytatywna
    0.65
     beſte
    0.65
    Activations Density 0.844%

    No Known Activations