© 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. 22-RES-MATRYOSHKA-DC
    7. 1558
    Prev
    Next
    INDEX
    Explanations

    references to regulations and government oversight

    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.22.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.22.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
     surla
    -0.79
    printStackTrace
    -0.76
    +#+
    -0.54
    Cllr
    -0.53
    cosse
    -0.52
     stained
    -0.50
    وردار
    -0.49
     OBITUARY
    -0.48
    paksa
    -0.48
    kkue
    -0.47
    POSITIVE LOGITS
     Federal
    0.98
     agency
    0.94
     Bureau
    0.91
     federal
    0.88
     Secretary
    0.84
    Federal
    0.83
     Agency
    0.81
    ederal
    0.81
     Congressional
    0.78
     USDA
    0.77
    Activations Density 1.779%

    No Known Activations