© 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. 2-RES-MATRYOSHKA-DC
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    references to a specific congressional oversight committee

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    board
    -0.57
    alia
    -0.50
     
    -0.49
    </h2>
    -0.48
    mag
    -0.47
     //
    -0.47
    yal
    -0.47
     lä
    -0.47
     commissioners
    -0.46
    scal
    -0.45
    POSITIVE LOGITS
     Committee
    3.53
     committee
    3.50
    Committee
    3.42
     COMMITTEE
    3.30
     committees
    3.16
     Committees
    3.13
    committee
    3.11
    committees
    2.45
     comité
    1.98
    mittee
    1.92
    Activations Density 0.006%

    No Known Activations