© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    evapor

    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
    defineProperty
    -0.55
    coglie
    -0.54
     kim
    -0.49
     Савезне
    -0.49
     mell
    -0.48
     llo
    -0.46
     externi
    -0.44
     Fail
    -0.44
     Hunter
    -0.44
     سي
    -0.43
    POSITIVE LOGITS
    bootstrapcdn
    0.63
     jadx
    0.60
    adpleegd
    0.60
    出版年
    0.60
    jsii
    0.57
    KommentareTeilen
    0.57
     parlour
    0.55
     élégante
    0.53
     Alcott
    0.53
    LayoutStyle
    0.52
    Activations Density 0.000%

    No Known Activations