© 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. 5330
    Prev
    Next
    INDEX
    Explanations

    of

    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
     المعيارى
    -0.72
     Infórmanos
    -0.72
     ujednoznacz
    -0.62
    ⓧ
    -0.60
    참고
    -0.60
    Personendaten
    -0.60
    nosaurus
    -0.59
    adaptiveStyles
    -0.59
    webElementXpaths
    -0.59
    :✨
    -0.57
    POSITIVE LOGITS
     publishing
    0.56
     using
    0.50
     developing
    0.49
     announcing
    0.49
     them
    0.48
     uploading
    0.46
     implementing
    0.46
     հղումներ
    0.45
     it
    0.45
     reporting
    0.44
    Activations Density 0.001%

    No Known Activations