© 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. 0-RES-MATRYOSHKA-DC
    7. 14398
    Prev
    Next
    INDEX
    Explanations

    whether a specific thread has been marked as dead or locked during traversal

    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
     Visitors
    -0.93
     visitors
    -0.91
    Visitors
    -0.88
     visitor
    -0.88
     GUEST
    -0.87
     guests
    -0.86
     guest
    -0.85
     Guest
    -0.84
    guest
    -0.83
     Visitor
    -0.82
    POSITIVE LOGITS
     visited
    1.92
    visited
    1.56
     Visited
    1.48
    Visited
    1.11
     frequented
    0.73
     visitó
    0.71
    bitField
    0.63
     attended
    0.62
     met
    0.62
    UObject
    0.61
    Activations Density 0.001%

    No Known Activations