© 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. 20243
    Prev
    Next
    INDEX
    Explanations

    terms related to the enforcement of laws or regulations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.66
     travellers
    -0.63
    sap
    -0.61
     Scherer
    -0.60
    assium
    -0.59
     Beziehungen
    -0.58
     dati
    -0.57
     Cardoso
    -0.56
     pymysql
    -0.55
     cap
    -0.55
    POSITIVE LOGITS
     enforcement
    1.36
     Enforcement
    1.28
    Enforcement
    1.23
    enforcement
    1.23
    FORCEMENT
    1.13
     enforcing
    1.01
     enforce
    0.98
     enforced
    0.93
    Datuak
    0.90
     Monfieur
    0.86
    Activations Density 0.005%

    No Known Activations