© 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. 24-RES-MATRYOSHKA-DC
    7. 371
    Prev
    Next
    INDEX
    Explanations

    legal language, especially related to judgments, decrees, and court proceedings

    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.24.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.24.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
    MigrationBuilder
    -0.65
    uldig
    -0.56
     ModelExpression
    -0.53
    andung
    -0.49
    ArgumentParser
    -0.49
     autorytatywna
    -0.48
    市镇
    -0.48
     sophistication
    -0.48
     coper
    -0.46
     ARGUMENT
    -0.46
    POSITIVE LOGITS
     orders
    0.96
     order
    0.94
    order
    0.79
     Orders
    0.79
    orders
    0.78
     decree
    0.74
    Orders
    0.73
     Order
    0.71
     ordering
    0.71
    Order
    0.70
    Activations Density 2.707%

    No Known Activations