© 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. 13679
    Prev
    Next
    INDEX
    Explanations

    references to individuals held in detention

    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
     jail
    -1.13
     prison
    -0.90
     Jail
    -0.82
    LLocation
    -0.80
     ſte
    -0.69
    jail
    -0.68
    WarningLevel
    -0.66
     ouvido
    -0.65
    CppMethod
    -0.64
    Jail
    -0.64
    POSITIVE LOGITS
     prisoner
    2.36
     prisoners
    2.27
     Prisoners
    1.92
     Prisoner
    1.88
     prisonniers
    1.07
     captives
    0.97
    prison
    0.95
     prision
    0.95
     Gefang
    0.82
     captive
    0.74
    Activations Density 0.007%

    No Known Activations