© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1130
    Prev
    Next
    INDEX
    Explanations

    words that are associated with legal proceedings such as trials and judgments

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stateMutability
    -0.54
     Habe
    -0.54
    arre
    -0.54
    Datuak
    -0.52
     <<<<<<<<<<<<<<
    -0.50
    glie
    -0.49
    WireFormatLite
    -0.49
    ropo
    -0.49
     wpis
    -0.48
     }));
    -0.47
    POSITIVE LOGITS
     verdict
    1.03
     jury
    0.99
     Verdict
    0.88
     verdicts
    0.87
     juries
    0.79
    Jury
    0.78
    Verdict
    0.74
     Jury
    0.73
    jury
    0.72
     jurado
    0.70
    Activations Density 1.177%

    No Known Activations