© 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. 1-RES-MATRYOSHKA-DC
    7. 470
    Prev
    Next
    INDEX
    Explanations

    references to legal provisions, rules, or statutory requirements

    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
     متعلقه
    -0.82
    HomeAsUp
    -0.79
    viewDidLoad
    -0.68
    ActionCreators
    -0.68
     Bole
    -0.67
     estimés
    -0.63
    DataAnnotations
    -0.61
    tvguidetime
    -0.60
    Portail
    -0.60
    InvalidProtocol
    -0.60
    POSITIVE LOGITS
     provide
    3.14
     provided
    3.14
    provide
    2.97
     Provide
    2.95
     provides
    2.92
     providing
    2.91
    Provide
    2.88
    provided
    2.78
     Provided
    2.73
     Providing
    2.73
    Activations Density 1.094%

    No Known Activations