© 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. 4056
    Prev
    Next
    INDEX
    Explanations

    references to time durations or time-related measurements

    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
     decade
    -1.18
     year
    -1.13
     YEAR
    -1.04
    year
    -1.02
     HOUR
    -1.02
     hour
    -1.01
    YEAR
    -0.95
    decade
    -0.94
    hour
    -0.91
    Year
    -0.91
    POSITIVE LOGITS
     days
    1.80
     Days
    1.56
    Days
    1.42
     DAYS
    1.37
    days
    1.30
     días
    1.13
     Tagen
    1.08
    DAYS
    0.95
     дни
    0.92
     jours
    0.92
    Activations Density 0.090%

    No Known Activations