© 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. 92694
    Prev
    Next
    INDEX
    Explanations

    the

    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
    leetcode
    -0.54
    Jeografia
    -0.54
    viewDidLoad
    -0.48
     --;
    -0.48
    --;
    -0.47
     Quadrant
    -0.46
     mené
    -0.46
    MigrationBuilder
    -0.46
    出版年
    -0.46
     prêts
    -0.44
    POSITIVE LOGITS
     كومونز
    0.53
     dynamically
    0.53
    ViewImports
    0.52
    ISupport
    0.52
     "..\..\
    0.51
     vaid
    0.51
    asyarakat
    0.50
     EoL
    0.50
     Bochum
    0.50
     armoured
    0.49
    Activations Density 0.000%

    No Known Activations