© 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. 1246
    Prev
    Next
    INDEX
    Explanations

    references to specific large-scale visual or graphical content, particularly images, figures, or visual designs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Total
    -0.96
    total
    -0.96
     Total
    -0.90
     total
    -0.86
     TOTAL
    -0.85
    TOTAL
    -0.79
    :]:
    -0.77
    RegressionTest
    -0.77
     JpaRepository
    -0.73
     Insgesamt
    -0.73
    POSITIVE LOGITS
     full
    4.63
    full
    4.22
    Full
    4.16
     Full
    4.13
    FULL
    3.70
     FULL
    3.69
    フル
    2.55
     peł
    2.52
     vollen
    2.48
     fuller
    2.47
    Activations Density 1.191%

    No Known Activations