© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1296
    Prev
    Next
    INDEX
    Explanations

    references to synchronization protocols and packet-related protocol information

    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
     Efq
    -0.91
    tvguidetime
    -0.84
     leaſt
    -0.72
     raiſ
    -0.72
     Majefty
    -0.70
     Bellas
    -0.69
     ſeveral
    -0.69
    addClass
    -0.69
     Shakspeare
    -0.68
    iempo
    -0.68
    POSITIVE LOGITS
     protocol
    1.82
     Protocol
    1.82
    Protocol
    1.60
    protocol
    1.59
     protocols
    1.55
     extract
    1.55
     Protocols
    1.48
     extraction
    1.48
     PROTOCOL
    1.47
     Extract
    1.46
    Activations Density 1.006%

    No Known Activations