© 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. 3-RES-MATRYOSHKA-DC
    7. 1162
    Prev
    Next
    INDEX
    Explanations

    the word "share"

    oai_token-act-pair · gemini-2.0-flash
    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
    ergies
    -0.61
    /*---
    -0.59
    vál
    -0.56
    さく
    -0.54
    玄
    -0.52
    Año
    -0.51
     sı
    -0.51
    WebVitals
    -0.51
    getResultList
    -0.50
     erin
    -0.49
    POSITIVE LOGITS
     share
    3.33
     shares
    3.16
    share
    3.11
     sharing
    3.06
     Share
    3.00
     SHARE
    2.95
     shared
    2.94
     Sharing
    2.92
    Share
    2.89
    shares
    2.81
    Activations Density 0.132%

    No Known Activations