© 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. 12-RES-MATRYOSHKA-DC
    7. 20167
    Prev
    Next
    INDEX
    Explanations

    mentions of "duty" in various contexts related to cycles and performance metrics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Macca
    -0.81
     IAP
    -0.79
     Cardinals
    -0.79
     Layla
    -0.78
     Siamese
    -0.77
     Vang
    -0.77
     DiCaprio
    -0.76
     CMC
    -0.74
     OGS
    -0.74
     rehabilitate
    -0.72
    POSITIVE LOGITS
     Duty
    1.08
     duty
    0.95
     DUTY
    0.94
    Duty
    0.93
    duty
    0.81
    WithFormat
    0.80
     Duties
    0.78
     duties
    0.78
    DUT
    0.77
     DUT
    0.71
    Activations Density 0.008%

    No Known Activations