© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    instructions or references related to protocol stack control functions

    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
     he
    -0.47
     IP
    -0.45
     even
    -0.45
    an
    -0.43
     an
    -0.42
     es
    -0.42
     o
    -0.41
     total
    -0.41
     le
    -0.41
     
    -0.40
    POSITIVE LOGITS
     nahilalakip
    1.17
    aarrggbb
    1.05
     समीक्षाओं
    1.01
     Италијани
    1.01
    ########.
    0.96
    Aholisi
    0.96
     surla
    0.95
     nakalista
    0.94
    évaluateur
    0.93
    Diwedd
    0.92
    Activations Density 0.496%

    No Known Activations