© 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. 528
    Prev
    Next
    INDEX
    Explanations

    the word "site" or "website."

    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
     tvar
    -0.54
     ke
    -0.52
    ^{
    -0.51
     room
    -0.51
    rd
    -0.50
    ionario
    -0.50
     equipped
    -0.49
    ity
    -0.48
    rio
    -0.48
    ke
    -0.48
    POSITIVE LOGITS
     site
    3.39
     Site
    3.39
     Sites
    3.23
    Site
    3.19
     sites
    3.17
     SITE
    3.08
    site
    3.00
    Sites
    2.98
    sites
    2.97
    SITE
    2.97
    Activations Density 0.146%

    No Known Activations