© 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. 1-CLT-HP
    7. 9300
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical articles

    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
     workday
    -1.25
    EndInit
    -0.94
     NSCoder
    -0.90
     AssemblyProduct
    -0.87
     Normdatei
    -0.84
     '\\;'
    -0.79
     AssemblyCulture
    -0.75
     MotionEvent
    -0.74
    ftagPool
    -0.74
     ویکی‌پدی
    -0.73
    POSITIVE LOGITS
    fire
    0.48
    läufer
    0.46
     dynamic
    0.45
     loose
    0.45
     limit
    0.43
    dat
    0.43
    arto
    0.43
    p
    0.42
    addr
    0.42
     start
    0.42
    Activations Density 0.035%

    No Known Activations