© 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. 4201
    Prev
    Next
    INDEX
    Explanations

    references to correctional officers involved in incident reports

    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
     police
    -1.02
     Police
    -1.02
    Police
    -0.98
     POLICE
    -0.96
    police
    -0.96
     FBI
    -0.82
    Polizei
    -0.78
    migrationBuilder
    -0.76
     polícia
    -0.75
    complexContent
    -0.74
    POSITIVE LOGITS
     officer
    2.50
     officers
    2.47
     Officer
    2.36
     Officers
    2.34
     OFFICER
    2.34
    officer
    2.19
     OFFICERS
    2.14
    officers
    2.13
    Officers
    2.11
    Officer
    2.08
    Activations Density 0.050%

    No Known Activations