© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    references to committees and their roles or actions

    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
     Knapp
    -0.64
    …
    -0.61
    …”
    -0.60
    :”
    -0.60
    ctive
    -0.60
    ’
    -0.60
     “
    -0.59
     ‘
    -0.58
     FR
    -0.57
     Stevenson
    -0.57
    POSITIVE LOGITS
     Committees
    1.52
     committees
    1.47
    committees
    1.41
    committee
    1.30
     COMMITTEE
    1.28
     Committee
    1.23
     committee
    1.15
    Committee
    1.14
    usschuss
    1.09
     Czechos
    1.05
    Activations Density 0.009%

    No Known Activations