© 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-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1314
    Prev
    Next
    INDEX
    Explanations

    references to specific prominent individuals and their names

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    toObject
    -0.59
     Weeknd
    -0.59
     Metcalf
    -0.56
     munt
    -0.54
     Hemsworth
    -0.53
    gypten
    -0.53
    Schwer
    -0.52
     Auvergne
    -0.52
    leneck
    -0.51
     méta
    -0.51
    POSITIVE LOGITS
     Mar
    3.81
    Mar
    3.61
     mar
    3.59
     MAR
    3.58
    mar
    3.38
    MAR
    3.36
     Мар
    2.38
     margin
    2.33
     marg
    2.27
     Margin
    2.25
    Activations Density 0.331%

    No Known Activations