© 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. 24-RES-MATRYOSHKA-DC
    7. 907
    Prev
    Next
    INDEX
    Explanations

    references to time, mainly "last [day/week/year]"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Days
    -0.81
     Years
    -0.80
     Days
    -0.75
    Years
    -0.69
     DAYS
    -0.69
     YEARS
    -0.69
     Hours
    -0.68
    DAYS
    -0.66
    Hours
    -0.66
    days
    -0.61
    POSITIVE LOGITS
     week
    1.27
     year
    1.16
     month
    1.08
     weekend
    1.06
     evening
    1.04
     night
    1.02
     summer
    1.02
     season
    0.99
     morning
    0.98
     spring
    0.92
    Activations Density 0.284%

    No Known Activations