© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25468
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and discussions related to trials or legal proceedings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    gex
    -0.51
    uchtet
    -0.51
    print
    -0.47
     fieltro
    -0.47
    IVersion
    -0.47
    OfYear
    -0.46
     hombros
    -0.46
     dispoz
    -0.46
    étaire
    -0.45
    InBytes
    -0.45
    POSITIVE LOGITS
    DockStyle
    0.78
    AnimationsModule
    0.66
     meanwhile
    0.65
    
    0.65
    ScopeManager
    0.64
    AccessorTable
    0.63
    !*\
    0.62
     already
    0.59
    TagMode
    0.59
    medriver
    0.59
    Activations Density 0.112%

    No Known Activations