© 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. 6807
    Prev
    Next
    INDEX
    Explanations

    references to historical and cultural periods or events

    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
     means
    -0.81
    means
    -0.75
    Means
    -0.73
     mean
    -0.71
    MEAN
    -0.71
     Mean
    -0.70
     Means
    -0.70
    Mean
    -0.68
    Media
    -0.67
    存于互联网档案馆
    -0.66
    POSITIVE LOGITS
     mid
    3.77
     Mid
    3.52
    Mid
    3.41
    mid
    3.25
     MID
    2.84
    MID
    2.73
     mids
    2.27
    mids
    2.13
     midpoint
    1.91
     midterm
    1.90
    Activations Density 0.043%

    No Known Activations