© 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. 12090
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific logical or temporal conjunctions and expressions indicating conditions or timing

    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
    marginHorizontal
    -0.54
    AndEndTag
    -0.53
     DeV
    -0.52
     ligiloj
    -0.51
    ElementException
    -0.50
     mates
    -0.48
    Brainz
    -0.48
     בן
    -0.48
    ViewImports
    -0.48
    بالإ
    -0.47
    POSITIVE LOGITS
     wenn
    2.23
     waar
    1.65
     weil
    1.59
     Wenn
    1.56
    Wenn
    1.48
     sobald
    1.35
    wenn
    1.30
     zodat
    1.28
     omdat
    1.24
     daß
    1.21
    Activations Density 0.003%

    No Known Activations