© 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. 2-RES-MATRYOSHKA-DC
    7. 7171
    Prev
    Next
    INDEX
    Explanations

    synchronization signals related to system or data synchronization processes

    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
     Pelleg
    -0.64
    adamia
    -0.59
     OBIT
    -0.58
     Complaints
    -0.58
     FishBase
    -0.58
     numberWith
    -0.58
    beiter
    -0.58
     Shetland
    -0.57
     EClass
    -0.57
     Grinder
    -0.57
    POSITIVE LOGITS
    sync
    2.88
     sync
    2.78
    Sync
    2.72
     Sync
    2.64
    SYNC
    2.31
     synchronization
    2.23
     synchronize
    2.09
     syncing
    2.09
     synchron
    2.06
     SYNC
    2.03
    Activations Density 0.010%

    No Known Activations