© 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. 1-RES-MATRYOSHKA-DC
    7. 179
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or days

    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
    RectangleBorder
    -0.73
     procedere
    -0.71
    endregion
    -0.67
     préalable
    -0.66
    WriteLiteral
    -0.66
    hésite
    -0.66
    tawesome
    -0.65
     laude
    -0.65
    PerformLayout
    -0.63
    exitRule
    -0.63
    POSITIVE LOGITS
     day
    3.97
    day
    3.61
     Day
    3.53
    Day
    3.45
     DAY
    3.36
    DAY
    3.27
     days
    2.69
    days
    2.63
     día
    2.55
     Days
    2.52
    Activations Density 0.751%

    No Known Activations