© 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. 0-CLT-HP
    7. 43042
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    jani
    -1.29
     Yup
    -0.75
    Yup
    -0.68
     metropolis
    -0.60
     Yep
    -0.59
    ISIONS
    -0.57
    Yep
    -0.56
    出版年
    -0.56
    Điều
    -0.55
     Metropolis
    -0.52
    POSITIVE LOGITS
     pylint
    0.60
     للمعارف
    0.57
     AssemblyProduct
    0.54
     بيها
    0.54
    >{@
    0.52
    Sied
    0.51
     yoda
    0.51
     comarca
    0.51
    Rozm
    0.51
    hobia
    0.48
    Activations Density 0.493%

    No Known Activations