© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    references to the word "when" in context

    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
     how
    -1.38
     WHETHER
    -1.13
     apakah
    -1.13
     why
    -1.10
     whether
    -1.10
    whether
    -1.09
     who
    -1.07
    how
    -1.04
     How
    -1.02
     HOW
    -0.98
    POSITIVE LOGITS
     when
    2.50
    when
    2.17
    When
    2.00
     When
    1.95
     cuando
    1.87
     quando
    1.85
     WHEN
    1.82
    cuando
    1.66
    WHEN
    1.65
     когда
    1.60
    Activations Density 0.185%

    No Known Activations