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. 0-CLT-HP
    4. 40795
    Prev
    Next
    INDEX
    Explanations

    recycled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recycle
    -0.80
    recycle
    -0.79
     Recycled
    -0.76
    ide
    -0.75
     recycled
    -0.72
     Recycling
    -0.71
    
    -0.71
     redeem
    -0.69
    /*
    -0.69
     reciclaje
    -0.68
    POSITIVE LOGITS
    less
    0.67
    wise
    0.56
     and
    0.55
    tn
    0.55
     of
    0.54
     with
    0.54
    ting
    0.54
     inc
    0.52
     loss
    0.50
    Wise
    0.50
    Activations Density 0.092%

    No Known Activations