© 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. 5-CLT-HP
    7. 3980
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    seguida
    -0.74
     חיצוניים
    -0.66
     répondu
    -0.65
    DoubleQuotes
    -0.65
     instantly
    -0.64
     Instantly
    -0.62
    Immediately
    -0.61
     Immediately
    -0.60
     aussitôt
    -0.60
     chóng
    -0.59
    POSITIVE LOGITS
     AssemblyProduct
    0.68
     every
    0.62
     the
    0.57
    WebElementEntity
    0.55
    StoryboardSegue
    0.52
    CppMethod
    0.52
     Paglinawan
    0.52
     a
    0.51
    Viitteet
    0.50
    UTIVE
    0.50
    Activations Density 0.001%

    No Known Activations