© 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. 2-RES-MATRYOSHKA-DC
    7. 4979
    Prev
    Next
    INDEX
    Explanations

    references to the word "As" indicating the beginning of explanations or descriptions

    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
     kasarigan
    -0.56
     correctes
    -0.56
     نق
    -0.55
    ・)
    -0.52
     Metallurgy
    -0.52
     sputum
    -0.52
     querían
    -0.52
     plaît
    -0.50
    THAN
    -0.49
     būti
    -0.49
    POSITIVE LOGITS
     As
    2.19
    As
    2.03
     AS
    0.93
     arsenic
    0.84
     Ас
    0.80
    AsString
    0.75
    '));
    0.75
     doInBackground
    0.74
     Assignee
    0.73
     ASC
    0.72
    Activations Density 0.076%

    No Known Activations