© 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. 170
    Prev
    Next
    INDEX
    Explanations

    instances of legal phrases and terminology related to court proceedings and their implications

    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
    duğu
    -0.47
     tempio
    -0.44
     creș
    -0.44
     prochaines
    -0.43
     yaptığı
    -0.41
    chowy
    -0.41
    xtures
    -0.41
    此
    -0.40
     combination
    -0.40
     læng
    -0.40
    POSITIVE LOGITS
    ผู้
    0.65
     politicians
    0.64
     members
    0.62
     investors
    0.61
     journalists
    0.61
     fellow
    0.60
    enterOuterAlt
    0.60
     students
    0.60
     financiers
    0.59
     young
    0.58
    Activations Density 7.007%

    No Known Activations