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. 1-CLT-HP
    4. 11109
    Prev
    Next
    INDEX
    Explanations

    paper

    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
     côtés
    -0.52
     deberes
    -0.46
    afficheront
    -0.46
     medlem
    -0.45
    الحياه
    -0.45
     titulares
    -0.44
     soins
    -0.44
    existsSync
    -0.43
     réguli
    -0.43
     cortas
    -0.43
    POSITIVE LOGITS
    
    0.91
    ⓧ
    0.71
    出版年
    0.68
     itſelf
    0.65
    ècie
    0.62
    IUrlHelper
    0.60
     quail
    0.60
    +:+
    0.59
     aphid
    0.59
     propOrder
    0.59
    Activations Density 0.007%

    No Known Activations