© 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. 4132
    Prev
    Next
    INDEX
    Explanations

    symbol

    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
    XtraGrid
    -0.66
    Portale
    -0.65
    ########.
    -0.64
     NgModule
    -0.58
     للاسماء
    -0.56
    EndProject
    -0.55
     Italijani
    -0.54
    jsxFileName
    -0.54
     /\.(
    -0.53
    Portail
    -0.52
    POSITIVE LOGITS
     of
    1.16
     closely
    0.53
     ویکی‌پدیا
    0.50
     parlato
    0.47
     found
    0.47
     varying
    0.46
    chapper
    0.46
    Còn
    0.46
     combining
    0.45
    copyOf
    0.45
    Activations Density 0.005%

    No Known Activations