© 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. 216
    Prev
    Next
    INDEX
    Explanations

    scientific terms and related concepts in technical 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
    Negative Logits
     Moscú
    -0.57
     surpresa
    -0.56
     Económica
    -0.54
     nästa
    -0.53
     quizá
    -0.52
     conclure
    -0.50
     overras
    -0.49
    affaires
    -0.49
     Others
    -0.48
     Constitucional
    -0.48
    POSITIVE LOGITS
    OGND
    0.63
    AddTagHelper
    0.59
    AddHtmlAttribute
    0.57
    bootstrapcdn
    0.56
     SqlDbType
    0.54
    LEncoder
    0.54
     BoxDecoration
    0.53
    thâu
    0.53
    ValueStyle
    0.52
     nahilalakip
    0.52
    Activations Density 4.521%

    No Known Activations