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. 40824
    Prev
    Next
    INDEX
    Explanations

    painting, art, programming

    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
     painting
    -1.02
    Root
    -0.84
     Painting
    -0.79
    root
    -0.73
    roots
    -0.73
     Root
    -0.71
    painting
    -0.71
     painted
    -0.69
    Painting
    -0.67
    Roots
    -0.66
    POSITIVE LOGITS
    IndentedString
    0.81
    httphttps
    0.70
    pushFollow
    0.69
     AttributeSet
    0.69
    FormTagHelper
    0.63
    帖最后由
    0.63
     الرياضيه
    0.60
    Према
    0.60
    imentel
    0.59
    contentLoaded
    0.59
    Activations Density 1.163%

    No Known Activations