© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14847
    Prev
    Next
    INDEX
    Explanations

    references to police or law enforcement agencies

    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
    AsUp
    -1.02
     ſever
    -0.96
     themſelves
    -0.91
     ainfi
    -0.91
     Theſe
    -0.91
     Jefus
    -0.83
     ſche
    -0.82
     Reſ
    -0.82
     Monfieur
    -0.82
     raiſ
    -0.81
    POSITIVE LOGITS
     served
    0.53
     staff
    0.52
     serve
    0.50
     del
    0.49
    nonatomic
    0.49
     servizio
    0.47
    </b>
    0.47
    staff
    0.45
    制
    0.45
     stuff
    0.44
    Activations Density 0.019%

    No Known Activations