© 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. 137
    Prev
    Next
    INDEX
    Explanations

    words associated with legal or formal proceedings

    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
    SourceChecksum
    -0.49
    Étape
    -0.43
    MessageOf
    -0.42
    Rptr
    -0.42
    AndEndTag
    -0.41
    LinkId
    -0.39
     AssemblyTitle
    -0.38
    StoryboardSegue
    -0.37
    Personendaten
    -0.37
    +:+
    -0.36
    POSITIVE LOGITS
    UseVisualStyle
    0.50
     ویکی‌آمباردا
    0.48
    ThemeOverlay
    0.44
    Rüyada
    0.41
    IntoConstraints
    0.41
     informée
    0.40
     ostavi
    0.39
     Strö
    0.39
    AddTagHelper
    0.37
    ValueStyle
    0.37
    Activations Density 23.808%

    No Known Activations