© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    references to network socket objects

    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
     noDo
    -0.83
     împre
    -0.81
     nonatomic
    -0.80
    APORE
    -0.72
    ſelves
    -0.70
     tslint
    -0.70
    DeleteBehavior
    -0.70
     gjø
    -0.69
    RuleContext
    -0.69
     endregion
    -0.69
    POSITIVE LOGITS
    socket
    3.02
     socket
    2.98
    Socket
    2.86
     Socket
    2.77
     sockets
    2.34
    Sockets
    2.03
    sockets
    1.85
    SOCKET
    1.73
    sock
    1.41
     SOCK
    1.28
    Activations Density 0.008%

    No Known Activations