© 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. 379
    Prev
    Next
    INDEX
    Explanations

    references to financial or economic impacts related to legislation or public health issues

    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
     physical
    -0.43
     enable
    -0.42
    itatea
    -0.42
     Vordergrund
    -0.41
     terres
    -0.40
     systém
    -0.40
    baiki
    -0.40
     aspects
    -0.39
     removeAll
    -0.39
     literatura
    -0.39
    POSITIVE LOGITS
     ujednoznacz
    0.69
    KommentareTeilen
    0.69
     disambiguazione
    0.66
     reporter
    0.65
     חיצוניים
    0.65
     informée
    0.64
    reporter
    0.63
    ❋
    0.63
     оригіналу
    0.61
     propOrder
    0.61
    Activations Density 2.073%

    No Known Activations