© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5530
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     local
    -0.50
     referenties
    -0.47
     global
    -0.47
     null
    -0.45
     dehors
    -0.44
     primary
    -0.43
    levant
    -0.42
     Col
    -0.42
     Sal
    -0.41
     in
    -0.40
    POSITIVE LOGITS
     Roskov
    0.83
    ItemBackground
    0.81
     CreateTagHelper
    0.79
    !*\
    0.79
    RegressionTest
    0.76
    RenderAtEndOf
    0.76
    enumi
    0.74
     useRouter
    0.73
    ConverterFactory
    0.73
     viewDidLoad
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.