© 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. 32374
    Prev
    Next
    INDEX
    Explanations

    references to legal statements and their implications

    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
    خاذ
    -0.78
     Decker
    -0.73
    ltä
    -0.71
    MLLoader
    -0.70
     AdapterView
    -0.70
    wußt
    -0.68
    ={<
    -0.68
    reux
    -0.67
    ichy
    -0.67
     Dore
    -0.66
    POSITIVE LOGITS
     Statements
    1.05
    Statements
    1.02
    statements
    0.98
     statements
    0.98
     Statement
    0.94
    statement
    0.92
     statement
    0.89
    Statement
    0.88
     STATEMENTS
    0.88
     STATEMENT
    0.85
    Activations Density 0.024%

    No Known Activations