© 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. 0-RES-MATRYOSHKA-DC
    7. 11856
    Prev
    Next
    INDEX
    Explanations

    instances where enforcement or application of rules, regulations, or authority is emphasized

    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
     Enforcement
    -0.93
    Enforcement
    -0.66
     prochains
    -0.65
    enforcement
    -0.65
     enforcement
    -0.65
    ArrowToggle
    -0.61
    RegressionTest
    -0.60
     Spectrometry
    -0.58
    μερα
    -0.57
     operacional
    -0.57
    POSITIVE LOGITS
     enforce
    2.20
     enforcing
    1.32
     enforced
    1.19
    enforce
    1.13
    بوابة
    0.69
     impose
    0.64
    fjspx
    0.63
    AccessorTable
    0.63
     strict
    0.60
    principalColumn
    0.56
    Activations Density 0.001%

    No Known Activations