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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13319
    Prev
    Next
    INDEX
    Explanations

    references to disclosure information in legal and contractual documents

    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
     discloses
    -1.02
     disclosed
    -1.00
    Personensuche
    -0.93
    '};
    -0.73
    "});
    -0.72
    ']").
    -0.70
    '});
    -0.65
    cstdlib
    -0.65
    ')")
    -0.65
    `;
    
    -0.64
    POSITIVE LOGITS
     disclosure
    1.98
     Disclosure
    1.96
    disclosure
    1.84
    Disclosure
    1.77
     disclosures
    1.16
    CLOSURE
    1.00
    Disclosures
    0.80
    discovery
    0.57
    chowa
    0.57
     transparency
    0.54
    Activations Density 0.002%

    No Known Activations