© 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. 0-CLT-HP
    7. 41686
    Prev
    Next
    INDEX
    Explanations

    measures

    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
     measures
    -1.70
    measures
    -1.47
     Measures
    -1.41
    Measures
    -1.38
     MEASURES
    -1.21
     mesures
    -1.16
     mechanism
    -0.99
     mechanisms
    -0.98
     medidas
    -0.97
     misure
    -0.88
    POSITIVE LOGITS
    InjectAttribute
    0.79
    IntoConstraints
    0.71
     CreateTagHelper
    0.65
     ExecuteAsync
    0.65
    sizeCache
    0.65
    AddTagHelper
    0.64
     landfills
    0.62
    ArgumentParser
    0.60
     skulls
    0.60
     Solver
    0.58
    Activations Density 1.669%

    No Known Activations