© 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. 269
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    MLLoader
    -0.82
    KommentareTeilen
    -0.79
     Infórmanos
    -0.73
     nahilalakip
    -0.69
     Taktlose
    -0.69
    Geplaatst
    -0.66
     AttributeSet
    -0.65
     surla
    -0.64
    帖最后由
    -0.63
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
    .
    0.38
    1
    0.36
    GEBURTSDATUM
    0.34
     was
    0.33
    ).
    0.33
    Download
    0.32
    )))));
    0.32
    ↵
    0.31
    </blockquote>
    0.31
     campur
    0.31
    Activations Density 10.260%

    No Known Activations