Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31365
    Prev
    Next
    INDEX
    Explanations

    all forms of the word recycling

    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
    пові
    -0.63
     lumineux
    -0.63
     vœux
    -0.63
    quelize
    -0.63
     laiton
    -0.61
     fasse
    -0.60
    therford
    -0.60
     épais
    -0.59
    IsUnicode
    -0.59
     viewDid
    -0.59
    POSITIVE LOGITS
     recycling
    1.38
     recycled
    1.31
     recycle
    1.27
     Recycling
    1.21
    Recycling
    1.16
     Recy
    1.15
     Recycled
    1.14
     recycla
    1.13
     Recycle
    1.13
    Recycle
    1.12
    Activations Density 0.006%

    No Known Activations