© 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. 343
    Prev
    Next
    INDEX
    Explanations

    numerical data or outcomes related to results and discussions

    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
    phosa
    -0.44
     fatta
    -0.43
     influencing
    -0.41
    vollen
    -0.41
    derung
    -0.41
     Darío
    -0.40
    edonia
    -0.40
    paging
    -0.40
    ophor
    -0.40
    omen
    -0.40
    POSITIVE LOGITS
     defaultstate
    0.78
    AndEndTag
    0.68
    RegressionTest
    0.66
     <<<<<<<<<<<<<<
    0.62
    GEBURTSDATUM
    0.60
     nakalista
    0.60
    WebServlet
    0.58
    NameInMap
    0.58
    writeFieldEnd
    0.57
    ThroughAttribute
    0.55
    Activations Density 11.840%

    No Known Activations