© 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. 937
    Prev
    Next
    INDEX
    Explanations

    references to the admissibility and authenticity of legal evidence or records

    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
    AndEndTag
    -0.53
    invokeLater
    -0.51
    ities
    -0.49
     lẻ
    -0.46
    putExtra
    -0.43
    拓
    -0.42
     rowspan
    -0.42
    mie
    -0.42
    %'
    -0.41
     La
    -0.41
    POSITIVE LOGITS
    expandindo
    0.83
    tvguidetime
    0.80
     تانيه
    0.79
    Diweddarwch
    0.79
     Normdatei
    0.77
    parsedMessage
    0.68
    QMetaType
    0.67
     intptr
    0.63
    verwijspagina
    0.62
    Ecotoxicity
    0.61
    Activations Density 2.606%

    No Known Activations