© 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. 3800
    Prev
    Next
    INDEX
    Explanations

    references to a specific mathematical function or object in formal scientific or mathematical text

    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
     للاسماء
    -0.76
    存于互联网档案馆
    -0.75
     myſelf
    -0.74
     Hän
    -0.74
     DAI
    -0.73
     Talis
    -0.68
     cwt
    -0.67
    rsiniz
    -0.66
     hiér
    -0.66
     Armand
    -0.65
    POSITIVE LOGITS
    Phi
    2.13
     Phi
    1.74
     Phipps
    1.02
     Φ
    0.93
    Φ
    0.80
     Phila
    0.69
     Brookfield
    0.68
     Reeves
    0.66
     Phil
    0.65
    LabelTagHelper
    0.63
    Activations Density 0.022%

    No Known Activations