© 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. 16863
    Prev
    Next
    INDEX
    Explanations

    references to democracy and governance

    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
     AssemblyCulture
    -1.02
    ValueStyle
    -0.90
    elemField
    -0.86
     الحره
    -0.85
     ſich
    -0.83
    ThroughAttribute
    -0.82
     cherchés
    -0.82
     itſelf
    -0.82
     nahilalakip
    -0.80
     themſelves
    -0.80
    POSITIVE LOGITS
    떻
    0.39
    fre
    0.36
     Gla
    0.36
     two
    0.36
    asgi
    0.36
     per
    0.36
     United
    0.36
    offe
    0.36
     USA
    0.36
    podar
    0.36
    Activations Density 0.125%

    No Known Activations