© 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. 2-RES-MATRYOSHKA-DC
    7. 5037
    Prev
    Next
    INDEX
    Explanations

    references to serial communication protocols or signals

    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
    AnchorTagHelper
    -0.61
    antMatchers
    -0.57
     Lev
    -0.56
    UnsafeEnabled
    -0.55
    WebControls
    -0.55
    schirm
    -0.55
    Lev
    -0.52
    ruptedException
    -0.52
    IBOutlet
    -0.51
     CURIAM
    -0.51
    POSITIVE LOGITS
     serial
    3.20
     Serial
    2.91
    serial
    2.86
    Serial
    2.77
     SERIAL
    2.45
    SERIAL
    2.36
     serials
    1.84
     serialized
    1.59
     serialization
    1.57
    erial
    1.38
    Activations Density 0.012%

    No Known Activations