© 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. 94977
    Prev
    Next
    INDEX
    Explanations

    Unusual text/code/chemistry

    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
    zy
    -1.78
    ZY
    -1.03
    chie
    -0.96
    xy
    -0.94
     zy
    -0.92
    Zy
    -0.60
     xy
    -0.59
    zyj
    -0.55
     Zy
    -0.53
     plate
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    1.00
     estekak
    0.98
    ConstraintMaker
    0.97
     فريبيس
    0.90
    MENAFN
    0.88
    rungsseite
    0.88
     CreateTagHelper
    0.86
    Personensuche
    0.85
    ftagPool
    0.85
     NSCoder
    0.83
    Activations Density 2.126%

    No Known Activations