© 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. 447
    Prev
    Next
    INDEX
    Explanations

    numerical values accompanied by statistical measures of variability or significance

    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
    findpost
    -0.57
     médicale
    -0.48
    yarnpkg
    -0.47
     adota
    -0.47
     emprego
    -0.47
     personnalisée
    -0.46
     parlé
    -0.45
     miała
    -0.45
    protetor
    -0.45
     Verhält
    -0.44
    POSITIVE LOGITS
     wireType
    0.55
    TargetException
    0.47
     unknownFields
    0.47
    VIAF
    0.44
     nonUne
    0.43
     <>",
    0.42
    UIControlState
    0.42
     ±
    0.41
    Chham
    0.41
    PostInfinity
    0.41
    Activations Density 0.615%

    No Known Activations