© 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. 4-CLT-HP
    7. 671
    Prev
    Next
    INDEX
    Explanations

    graphic design, software

    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
     CreateTagHelper
    -0.72
    RegressionTest
    -0.60
    CloseOperation
    -0.59
    cookieParser
    -0.57
    MemoryWarning
    -0.53
    ритори
    -0.52
    aarrggbb
    -0.50
    .%
    -0.50
    PRM
    -0.50
     Paglinawan
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.72
    PreferredItem
    0.65
     LUMP
    0.61
     séparation
    0.53
     يتيمه
    0.53
    IndentedString
    0.52
     متحده
    0.51
    PUBLISH
    0.51
    ubility
    0.50
    iland
    0.50
    Activations Density 0.001%

    No Known Activations