© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4745
    Prev
    Next
    INDEX
    Explanations

    references to police organizations and law enforcement in Northern Ireland

    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
     West
    -1.01
     WEST
    -0.98
     west
    -0.98
    West
    -0.96
     East
    -0.90
    west
    -0.90
    WEST
    -0.90
     EAST
    -0.90
    East
    -0.88
     east
    -0.83
    POSITIVE LOGITS
     Northern
    3.31
    Northern
    3.25
     NORTHERN
    2.78
    northern
    2.58
     northern
    2.56
     Southern
    1.43
    Southern
    1.42
    thern
    1.26
     SOUTHERN
    1.26
    北方
    1.20
    Activations Density 0.030%

    No Known Activations