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. 12832
    Prev
    Next
    INDEX
    Explanations

    estimate

    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
    AndEndTag
    -1.02
    +#+#
    -0.91
    ConstraintMaker
    -0.80
     autorytatywna
    -0.75
    HasForeignKey
    -0.75
     وتسجيلات
    -0.75
    帖最后由
    -0.74
    
    -0.72
    tonsoft
    -0.71
    Havolalar
    -0.71
    POSITIVE LOGITS
     zirc
    0.47
     Grenville
    0.47
     transpiration
    0.47
     volcano
    0.45
     sulfur
    0.44
     vmax
    0.44
     combustion
    0.43
     soil
    0.43
     Pallas
    0.43
     erythrocytes
    0.42
    Activations Density 0.007%

    No Known Activations