© 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. 1-RES-MATRYOSHKA-DC
    7. 63
    Prev
    Next
    INDEX
    Explanations

    references to specific times or conditions related to events or processes

    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
    ArrowToggle
    -0.81
    tagHelper
    -0.72
     weiterer
    -0.64
    NonQuery
    -0.61
    Init
    -0.60
    oges
    -0.56
    ukų
    -0.56
     Emery
    -0.56
    verticalLayout
    -0.56
    ます
    -0.54
    POSITIVE LOGITS
     when
    3.05
    when
    2.61
     WHEN
    2.34
     cuando
    2.27
     quando
    2.23
     if
    2.11
     When
    2.11
     wanneer
    2.11
    When
    2.06
    WHEN
    2.06
    Activations Density 3.373%

    No Known Activations