© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5976
    Prev
    Next
    INDEX
    Explanations

    references to significant legal or judicial concepts and reasoning

    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
     respekt
    -0.61
     respectful
    -0.60
     RESPECT
    -0.59
    كويكب
    -0.58
     respecter
    -0.56
    :✨
    -0.56
    Respect
    -0.56
    üsü
    -0.55
     naturelles
    -0.55
     disrespectful
    -0.55
    POSITIVE LOGITS
     regard
    2.91
    regard
    2.25
     Regard
    2.22
     regards
    2.08
     REGARD
    1.90
     regarded
    1.70
    regards
    1.50
     Regards
    1.26
     regarding
    1.20
     Regarding
    1.18
    Activations Density 0.007%

    No Known Activations