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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    opened

    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
     viewDidLoad
    -0.54
    PropertyChanging
    -0.52
     noqa
    -0.52
     MainAxisSize
    -0.51
    ContentAsync
    -0.50
    TagHelpers
    -0.48
     erfolgte
    -0.47
    ynb
    -0.47
    WaitGroup
    -0.46
     Shu
    -0.44
    POSITIVE LOGITS
    bootstrapcdn
    0.72
    IUrlHelper
    0.58
    Grüße
    0.58
    modelBuilder
    0.57
    titleMargin
    0.56
    Chham
    0.56
    Hå
    0.53
     Albu
    0.53
    ITUD
    0.52
     AssemblyProduct
    0.51
    Activations Density 0.012%

    No Known Activations