© 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. 7312
    Prev
    Next
    INDEX
    Explanations

    references to days or dates

    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
     nights
    -1.27
     evenings
    -1.18
     Nights
    -1.13
    Nights
    -1.09
     nightly
    -1.05
     tonight
    -1.02
     Tonight
    -1.02
     mornings
    -1.02
    Tonight
    -1.01
    nights
    -1.01
    POSITIVE LOGITS
     day
    1.61
     Day
    1.55
    Day
    1.34
     DAY
    1.30
    day
    1.13
     year
    0.94
    DAY
    0.93
     Year
    0.82
    year
    0.79
    Year
    0.78
    Activations Density 0.034%

    No Known Activations