© 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. 13018
    Prev
    Next
    INDEX
    Explanations

    specific message tokens or command identifiers related to message handling or protocol steps

    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
    BeginContext
    -0.91
    TagMode
    -0.91
    NewUrlParser
    -0.84
    principalTable
    -0.82
    ScopeManager
    -0.77
     ویکی‌آمباردا
    -0.74
     Taktlose
    -0.73
     useAppContext
    -0.72
    MessageTagHelper
    -0.71
    GraphicsUnit
    -0.71
    POSITIVE LOGITS
    MSG
    2.94
     MSG
    2.31
    タウン
    0.43
    prodi
    0.43
    staticmethod
    0.43
    伍
    0.43
    enumi
    0.43
     parem
    0.41
     sache
    0.40
    ajs
    0.40
    Activations Density 0.001%

    No Known Activations