© 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. 130
    Prev
    Next
    INDEX
    Explanations

    constructive or technical content related to programming, specifications, or software design

    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
    Not in Any Lists

    No Comments

    Negative Logits
     inoxidable
    -0.57
     armée
    -0.53
     juridique
    -0.50
     שוליים
    -0.50
     financières
    -0.50
     psicología
    -0.49
     financière
    -0.49
     judiciaire
    -0.49
     juridiques
    -0.49
     empêcher
    -0.48
    POSITIVE LOGITS
    :
    1.26
    _:
    1.02
    %:
    1.01
    :<
    0.99
    +:
    0.98
     _:
    0.98
     :
    0.98
    :</
    0.98
    |:
    0.95
    >):
    0.95
    Activations Density 1.321%

    No Known Activations