© 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. 5-CLT-HP
    7. 97662
    Prev
    Next
    INDEX
    Explanations

    folder/directory

    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
     folder
    -0.52
    kesh
    -0.47
     BoxFit
    -0.47
    ню
    -0.46
     noqa
    -0.46
    NewUrlParser
    -0.46
    ằng
    -0.45
    emark
    -0.44
     وصلة
    -0.44
    hamed
    -0.44
    POSITIVE LOGITS
     Structure
    0.77
    XmlAccessType
    0.75
    Structure
    0.66
     structure
    0.59
     CreateTagHelper
    0.58
     betweenstory
    0.58
    UVWXYZ
    0.58
     STRUCTURE
    0.57
     ModelExpression
    0.57
     Struktur
    0.55
    Activations Density 0.013%

    No Known Activations