© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    Code/numerical data/articles

    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
    awtextra
    -0.90
     дописавши
    -0.89
    AddTagHelper
    -0.86
    NameInMap
    -0.85
    MigrationBuilder
    -0.75
    MENAFN
    -0.73
    Referencies
    -0.66
    LookAnd
    -0.65
    ChildScrollView
    -0.64
    הערות
    -0.59
    POSITIVE LOGITS
    suri
    0.44
    myra
    0.43
     ExecuteAsync
    0.42
     Ignore
    0.42
    ,//
    0.42
    brokes
    0.41
     Wonder
    0.41
    pyl
    0.41
     COVER
    0.40
     velas
    0.39
    Activations Density 0.002%

    No Known Activations