© 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. 2-RES-MATRYOSHKA-DC
    7. 5840
    Prev
    Next
    INDEX
    Explanations

    references to scheduling or timetable information

    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
     Gauthier
    -0.63
     Lilian
    -0.55
     Roma
    -0.54
     tob
    -0.50
     ih
    -0.49
     sang
    -0.49
    Roma
    -0.49
     Organis
    -0.49
     Doria
    -0.49
     singer
    -0.49
    POSITIVE LOGITS
     schedule
    3.59
    schedule
    3.30
     Schedule
    3.28
     schedules
    3.22
     SCHEDULE
    3.11
    Schedule
    3.08
     Schedules
    3.00
     scheduling
    2.84
    SCHEDULE
    2.83
    schedules
    2.75
    Activations Density 0.011%

    No Known Activations