© 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. 421
    Prev
    Next
    INDEX
    Explanations

    statements indicating material or factual issues in legal 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
    itschrift
    -0.58
    timmen
    -0.57
    ustris
    -0.56
     Stimmen
    -0.56
     SearchView
    -0.55
    ENNA
    -0.54
    ună
    -0.54
    idians
    -0.53
    PostMapping
    -0.52
    jewództ
    -0.52
    POSITIVE LOGITS
     fact
    4.97
    fact
    4.28
     Fact
    3.86
    Fact
    3.72
     FACT
    3.59
    FACT
    3.17
     facts
    3.09
     Tatsache
    3.05
     Facts
    2.86
    facts
    2.80
    Activations Density 1.197%

    No Known Activations