© 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. 246
    Prev
    Next
    INDEX
    Explanations

    references to rings, especially in a romantic context involving marriage and commitment

    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
     yön
    -0.38
     Spe
    -0.35
     South
    -0.34
     free
    -0.34
    s
    -0.34
     action
    -0.34
    amata
    -0.33
     Adams
    -0.33
     Wild
    -0.32
     
    -0.32
    POSITIVE LOGITS
    TypedDataSet
    0.86
     betweenstory
    0.81
    expandindo
    0.79
     surla
    0.78
    şört
    0.77
     Administrativna
    0.76
    verwijspagina
    0.75
    évaluateur
    0.75
     ब्रेकडाउन
    0.73
     समीक्षक
    0.73
    Activations Density 7.491%

    No Known Activations