© 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. 6144
    Prev
    Next
    INDEX
    Explanations

    references to law, legal proceedings, or courtroom processes

    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
    WindowConstants
    -0.58
    الإنجليزية
    -0.57
     ویکی‌پدی
    -0.56
     Efq
    -0.56
    TestBed
    -0.55
    født
    -0.54
    StoryboardSegue
    -0.53
    पया
    -0.52
    WriteTagHelper
    -0.51
     CascadeType
    -0.50
    POSITIVE LOGITS
    HostException
    0.74
     Dea
    0.55
    ')}}">
    0.54
     Nasional
    0.53
    }\]
    0.52
     wikipagina
    0.52
    enumerate
    0.51
    zie
    0.51
    참고
    0.51
     ""],
    0.50
    Activations Density 0.431%

    No Known Activations