© 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. 33
    Prev
    Next
    INDEX
    Explanations

    phrases related to data representation and results in scientific writing

    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
    AddTagHelper
    -0.85
    tagHelperRunner
    -0.79
     мәкал
    -0.78
    ніципа
    -0.74
    parsedMessage
    -0.73
     ब्रेकडाउन
    -0.73
     Normdatei
    -0.72
    TagMode
    -0.70
    StructEnd
    -0.69
    RTEE
    -0.68
    POSITIVE LOGITS
    Figure
    0.70
    Fig
    0.62
     Figure
    0.61
     Fig
    0.57
     figures
    0.54
     shown
    0.50
    Figures
    0.49
     Figures
    0.49
     figure
    0.48
     charts
    0.48
    Activations Density 8.927%

    No Known Activations