© 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. 519
    Prev
    Next
    INDEX
    Explanations

    references to police, officers, and law enforcement actions

    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
     aDecoder
    -0.59
     onCreateView
    -0.59
    tagHelperRunner
    -0.58
    windowFixed
    -0.57
     usuf
    -0.57
    rungsseite
    -0.55
    __*/
    -0.55
    rawDesc
    -0.55
    abetes
    -0.53
    ătoare
    -0.53
    POSITIVE LOGITS
     police
    3.61
     Police
    3.34
    Police
    3.23
    police
    3.22
     POLICE
    3.11
     officers
    2.77
     officer
    2.70
     Officers
    2.66
     Officer
    2.63
    Officers
    2.61
    Activations Density 0.397%

    No Known Activations