© 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. 5-CLT-HP
    7. 97966
    Prev
    Next
    INDEX
    Explanations

    atter

    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
    Autoritní
    -0.62
     Paglinawan
    -0.42
    ్రామ
    -0.41
    Boxscore
    -0.40
    boat
    -0.39
    ards
    -0.39
     slings
    -0.38
    ast
    -0.38
     surla
    -0.38
    حي
    -0.37
    POSITIVE LOGITS
     AssemblyTitle
    0.68
    RectangleBorder
    0.63
     Normdatei
    0.62
    RegressionTest
    0.61
    setVerticalGroup
    0.61
     ujednoznacz
    0.61
    ruptedException
    0.60
    webElementGuid
    0.59
     AspNetCore
    0.58
    ValueStyle
    0.57
    Activations Density 0.003%

    No Known Activations