© 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. 6341
    Prev
    Next
    INDEX
    Explanations

    references to factual information or factual disputes in legal contexts

    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
    ]]
    -0.70
    "],
    -0.66
     ),
    -0.61
    useNewUrlParser
    -0.60
    olkata
    -0.60
    dafx
    -0.60
    bootstrapcdn
    -0.59
    "),
    -0.58
    '],
    -0.58
    ParallelGroup
    -0.57
    POSITIVE LOGITS
    usammen
    0.56
     词
    0.51
    Plaintiff
    0.50
     unilaterally
    0.49
    Mentions
    0.49
     paramString
    0.48
     Walling
    0.48
     commerciaux
    0.48
     innocently
    0.47
    פו
    0.47
    Activations Density 0.706%

    No Known Activations