© 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. 5765
    Prev
    Next
    INDEX
    Explanations

    i

    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
    invokeLater
    -0.66
    RegistryLite
    -0.62
     ujednoznacz
    -0.62
    UrlResolution
    -0.53
     AspNetCore
    -0.51
     članak
    -0.49
    jalá
    -0.49
    johns
    -0.48
    ttino
    -0.47
    ViewImports
    -0.46
    POSITIVE LOGITS
    รา
    0.58
     Secure
    0.57
    ThroughAttribute
    0.56
    enderror
    0.54
     bezeichneter
    0.50
     >=",
    0.50
     Triumph
    0.50
    undef
    0.49
     AUR
    0.48
    dify
    0.48
    Activations Density 0.005%

    No Known Activations