© 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. 14787
    Prev
    Next
    INDEX
    Explanations

    stock

    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
     stock
    -1.12
    Stock
    -1.09
     Stock
    -1.09
     STOCK
    -1.05
    stock
    -0.90
    STOCK
    -0.87
     Stocks
    -0.71
    Stocks
    -0.71
     stocks
    -0.66
    tock
    -0.65
    POSITIVE LOGITS
    IntoConstraints
    0.80
    inette
    0.66
    ings
    0.62
    +#+#
    0.61
    fjspx
    0.60
    GEBURTSDATUM
    0.59
     Италијани
    0.58
    AndEndTag
    0.56
    Personendaten
    0.56
    tvguidetime
    0.55
    Activations Density 0.040%

    No Known Activations