© 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. 413
    Prev
    Next
    INDEX
    Explanations

    statistical data and significance indicators in research results

    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
    ]")]
    -0.84
    ThroughAttribute
    -0.78
    ſelf
    -0.77
    UrlResolution
    -0.76
    ſelves
    -0.69
     disambiguazione
    -0.69
     snippetHide
    -0.67
     propOrder
    -0.67
    AndEndTag
    -0.66
    HasAnnotation
    -0.65
    POSITIVE LOGITS
     p
    0.45
    抗
    0.41
     Verb
    0.40
     interaction
    0.38
    p
    0.36
     Entrance
    0.35
     Selection
    0.33
    ベット
    0.33
     抗
    0.33
     schme
    0.32
    Activations Density 0.904%

    No Known Activations