© 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. 91260
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    NameInMap
    -0.70
    AccessorTable
    -0.63
    ifrance
    -0.56
    NUMX
    -0.53
     bénéfices
    -0.52
     Protección
    -0.52
    ussis
    -0.52
    olisian
    -0.51
    enix
    -0.49
    ondissement
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.63
    viewDidLoad
    0.54
    jsonwebtoken
    0.54
     resourceCulture
    0.54
     springfox
    0.52
    ViewImports
    0.52
     getopt
    0.52
    ToRead
    0.50
    TextAlignment
    0.49
     للاسماء
    0.49
    Activations Density 0.000%

    No Known Activations