© 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. 2-RES-MATRYOSHKA-DC
    7. 6292
    Prev
    Next
    INDEX
    Explanations

    references to specific years indicating a focus on historical timelines

    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
    Datuak
    -0.84
    oredCriteria
    -0.80
     calendriers
    -0.78
     Chwiliwch
    -0.65
     الاطلاع
    -0.62
    abestanden
    -0.59
    ########.
    -0.59
     Winaray
    -0.58
    ranean
    -0.57
     Gå
    -0.56
    POSITIVE LOGITS
     upbringing
    0.70
     Raised
    0.63
    Raised
    0.62
    AsUp
    0.59
     født
    0.59
     reared
    0.57
    quartered
    0.54
     childhood
    0.54
     HttpNotFound
    0.53
     raised
    0.53
    Activations Density 0.023%

    No Known Activations