© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30925
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically words like "yesterday" and "tomorrow."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Dane
    -0.72
     invitamos
    -0.71
    HtmlAttribute
    -0.69
    WritableDatabase
    -0.69
    anía
    -0.67
     carbu
    -0.65
    abestanden
    -0.64
    readInt
    -0.64
     Comstock
    -0.64
     entanto
    -0.63
    POSITIVE LOGITS
    ORROW
    0.97
    erom
    0.70
     tomorrow
    0.66
     Tomorrow
    0.64
    ρεύ
    0.63
    degener
    0.62
    Général
    0.62
     Arro
    0.61
     yesterday
    0.61
    لكتر
    0.60
    Activations Density 0.004%

    No Known Activations