© 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. 18-RES-MATRYOSHKA-DC
    7. 1203
    Prev
    Next
    INDEX
    Explanations

    references to time, especially dates, months, days of the week and years, and words like "last", "next" and "this" modifying those references

    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.18.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.18.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
    jadi
    -0.51
    AsUp
    -0.50
    Daily
    -0.47
     Allied
    -0.47
     sorts
    -0.47
     davon
    -0.45
    miştir
    -0.43
     Stirn
    -0.43
     Ever
    -0.43
    pii
    -0.42
    POSITIVE LOGITS
     year
    1.45
     season
    1.36
     month
    1.35
     week
    1.32
     summer
    1.12
     semester
    1.03
    season
    1.03
     semaine
    0.97
     seasons
    0.96
    month
    0.96
    Activations Density 0.710%

    No Known Activations