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. 22-CLT-HP
    4. 74254
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · 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
    1
    -1.19
    0
    -0.75
    2
    -0.67
    1
    -0.50
     du
    -0.49
    amp
    -0.49
     u
    -0.48
    jer
    -0.47
    chy
    -0.47
    u
    -0.47
    POSITIVE LOGITS
     متعلقه
    1.17
     мәкал
    1.05
    ValueStyle
    0.96
    
    0.94
     CreateTagHelper
    0.92
    ConstraintMaker
    0.91
     Мексичка
    0.91
     betweenstory
    0.90
    ंदीखरीदारी
    0.90
    IntoConstraints
    0.90
    Activations Density 0.016%

    No Known Activations