© 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. 30254
    Prev
    Next
    INDEX
    Explanations

    references to Congress or congressional matters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Lizzy
    -0.92
     Stip
    -0.79
    脚注の使い方
    -0.78
     Rosetta
    -0.77
    
    -0.76
    Bett
    -0.75
     Rtl
    -0.75
     Bettina
    -0.75
     Bute
    -0.74
     SwiftUI
    -0.73
    POSITIVE LOGITS
     Congress
    1.28
     CONGRESS
    1.11
    Congress
    1.08
     congress
    1.04
    congress
    0.98
    es
    0.82
     Congrès
    0.78
    GRESS
    0.76
    ressional
    0.73
     Cohn
    0.71
    Activations Density 0.007%

    No Known Activations