© 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. 1-RES-MATRYOSHKA-DC
    7. 1071
    Prev
    Next
    INDEX
    Explanations

    references to control mechanisms or control-related components

    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
     regulated
    -1.45
     governed
    -1.36
     Regulated
    -1.30
    regulated
    -1.28
     Rules
    -1.26
     ruled
    -1.23
    rules
    -1.23
     RULES
    -1.23
     rules
    -1.21
     Managed
    -1.20
    POSITIVE LOGITS
     control
    1.84
    control
    1.76
    Control
    1.74
     Control
    1.73
     CONTROL
    1.30
    CONTROL
    1.24
     contrôle
    0.85
    控制
    0.79
     Kontrolle
    0.73
     controle
    0.73
    Activations Density 0.082%

    No Known Activations