© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1194
    Prev
    Next
    INDEX
    Explanations

    Mythology/Fantasy

    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
     AssemblyCulture
    -0.73
    TagHelper
    -0.66
     تضيفلها
    -0.63
     المعيارى
    -0.58
    TabIndex
    -0.58
     שוליים
    -0.57
    IBarButtonItem
    -0.57
    ChildScrollView
    -0.56
    /*
    -0.55
    ForValue
    -0.54
    POSITIVE LOGITS
     Dummies
    0.63
    FromNib
    0.56
    NEYS
    0.49
    residents
    0.46
     Савезне
    0.46
    persons
    0.46
     Theaters
    0.46
    bodies
    0.46
    ULTS
    0.46
     clerks
    0.46
    Activations Density 0.006%

    No Known Activations