© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 123
    Prev
    Next
    INDEX
    Explanations

    dates and time frames related to events or studies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     varandra
    -0.50
    Bibliograf
    -0.46
    ammans
    -0.46
    ckså
    -0.45
     câte
    -0.44
     finnas
    -0.44
     inhoud
    -0.44
     ragioni
    -0.43
     ddelweddau
    -0.42
     zijne
    -0.41
    POSITIVE LOGITS
     weeks
    0.85
     week
    0.82
     time
    0.80
     morning
    0.79
     months
    0.77
     month
    0.77
     days
    0.75
     period
    0.73
     afternoon
    0.73
     September
    0.73
    Activations Density 11.151%

    No Known Activations