© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 215
    Prev
    Next
    INDEX
    Explanations

    references to days or parts of days

    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
    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
    ArgsConstructor
    -0.77
     combineReducers
    -0.69
    tawesome
    -0.69
    Nel
    -0.68
    鳥居
    -0.65
    +:+
    -0.64
     ním
    -0.63
    nel
    -0.63
     reen
    -0.63
     gustar
    -0.62
    POSITIVE LOGITS
     day
    2.27
    day
    2.13
    DAY
    1.99
     Day
    1.95
     DAY
    1.95
    Day
    1.93
     days
    1.77
     week
    1.75
    days
    1.74
     morning
    1.72
    Activations Density 0.760%

    No Known Activations