© 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. 363
    Prev
    Next
    INDEX
    Explanations

    legal jargon related to court proceedings, claims, motions, 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.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
    SourceChecksum
    -0.75
    +#+#
    -0.63
     Scales
    -0.51
    helves
    -0.48
    teto
    -0.47
    huana
    -0.47
    scales
    -0.46
    entiary
    -0.46
     BorderRadius
    -0.46
     tecnica
    -0.46
    POSITIVE LOGITS
     claims
    0.90
     suits
    0.85
     suit
    0.81
     lawsuits
    0.74
    claims
    0.72
     claim
    0.71
     action
    0.68
    suits
    0.68
     damages
    0.65
     Suits
    0.65
    Activations Density 2.716%

    No Known Activations