© 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. 913
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in courtroom proceedings and legal arguments

    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
     ‘
    -0.77
     “
    -0.72
     ’
    -0.59
     them
    -0.56
     who
    -0.55
     you
    -0.53
     They
    -0.52
    .”
    -0.52
    ’
    -0.50
    ‘
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.93
     plaintiff
    0.90
     defendants
    0.88
     defendant
    0.85
     plaintiffs
    0.84
     respondent
    0.81
    parsedMessage
    0.79
    kloped
    0.78
     Réponses
    0.78
    ंदीखरीदारी
    0.77
    Activations Density 1.576%

    No Known Activations