© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    sequences of text that include specific types of identifiers, codes, or symbols, often associated with data or reference markers

    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
    AccessorTable
    -0.58
    usercontent
    -0.53
     wireType
    -0.52
     reason
    -0.50
    elemField
    -0.49
    SerializedName
    -0.49
    jois
    -0.48
     Delphi
    -0.48
    呢
    -0.47
    talen
    -0.47
    POSITIVE LOGITS
    ário
    2.06
    $?
    1.79
    ários
    1.34
    ária
    1.26
    ÁRIO
    1.15
    árias
    0.87
    ⓧ
    0.70
    $_['
    0.62
     ligiloj
    0.61
    PageRoute
    0.59
    Activations Density 0.001%

    No Known Activations