© 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. 0-RES-MATRYOSHKA-DC
    7. 12161
    Prev
    Next
    INDEX
    Explanations

    references to specific sequence of words indicating a recurring event or transition

    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
    abestanden
    -0.68
    SourceChecksum
    -0.68
     مشين
    -0.62
    CommonModule
    -0.61
    DoubleQuotes
    -0.60
     AssemblyTitle
    -0.60
    ViewFeatures
    -0.60
    InStock
    -0.60
    DockStyle
    -0.60
    HostException
    -0.59
    POSITIVE LOGITS
    Then
    1.10
    Затем
    0.81
     Затем
    0.75
    THEN
    0.71
     Then
    0.69
    empereur
    0.64
    Puis
    0.62
    Dann
    0.62
    >'+
    0.56
     kuu
    0.56
    Activations Density 0.005%

    No Known Activations