© 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. 15049
    Prev
    Next
    INDEX
    Explanations

    references to message objects, particularly those involving the Message type or structure

    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
    LookAnd
    -0.79
    UnitTesting
    -0.78
    endpush
    -0.73
    webElementXpaths
    -0.73
     transférez
    -0.72
     betweenstory
    -0.72
     messages
    -0.71
     Normdatei
    -0.71
    theless
    -0.70
    MigrationBuilder
    -0.70
    POSITIVE LOGITS
    Message
    2.09
     Message
    0.76
    MESSAGE
    0.54
    在我
    0.50
    beni
    0.47
    当我
    0.46
    idom
    0.46
     vole
    0.45
    但我
    0.45
     wij
    0.45
    Activations Density 0.011%

    No Known Activations