© 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. 1-CLT-HP
    7. 14011
    Prev
    Next
    INDEX
    Explanations

    TA

    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
    帖最后由
    -0.60
    PhysRevLett
    -0.57
    ElementException
    -0.52
    JsonHelper
    -0.50
    awtextra
    -0.49
    AnchorTagHelper
    -0.48
     médicaux
    -0.48
    LabelTagHelper
    -0.48
     LoggerFactory
    -0.47
     WebApplication
    -0.47
    POSITIVE LOGITS
     lenker
    0.66
     AssemblyProduct
    0.55
    <<<<<<<<<<<<
    0.55
     الحره
    0.51
    tops
    0.51
    ane
    0.50
    GEBURTS
    0.49
     HG
    0.49
     gespe
    0.49
    ddr
    0.48
    Activations Density 0.019%

    No Known Activations