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. 40838
    Prev
    Next
    INDEX
    Explanations

    legal and technical documents

    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
    IContainer
    -0.94
    izr
    -0.92
     createSprite
    -0.91
     fallu
    -0.91
    fromnode
    -0.90
    expandindo
    -0.87
    
    -0.85
     propOrder
    -0.83
     Blame
    -0.82
     surla
    -0.81
    POSITIVE LOGITS
    s
    0.77
    ing
    0.59
    d
    0.54
    a
    0.49
    n
    0.49
    g
    0.44
    f
    0.44
    b
    0.44
    t
    0.44
    note
    0.42
    Activations Density 0.043%

    No Known Activations