© 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. 18-RES-MATRYOSHKA-DC
    7. 1458
    Prev
    Next
    INDEX
    Explanations

    legal language, including citations, court decisions, 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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    parsedMessage
    -0.58
     núm
    -0.56
    wantErr
    -0.55
     hâte
    -0.54
     NSCoder
    -0.54
    Liefs
    -0.52
    aturing
    -0.52
     riuscito
    -0.52
    SFD
    -0.52
     addItem
    -0.51
    POSITIVE LOGITS
     precedent
    1.09
     precedents
    0.96
     cases
    0.88
     case
    0.85
     precedence
    0.81
    cedent
    0.80
    Preced
    0.77
    preced
    0.76
     preced
    0.73
     jurisprudence
    0.73
    Activations Density 1.227%

    No Known Activations