© 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. 3047
    Prev
    Next
    INDEX
    Explanations

    Technical Writing

    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
     виправивши
    -0.63
    BitmapFactory
    -0.63
    uxxxx
    -0.62
     >=",
    -0.59
     للمعارف
    -0.58
    TagHelpers
    -0.57
     AttributeSet
    -0.56
     demografica
    -0.56
    ांकि
    -0.54
     oubli
    -0.53
    POSITIVE LOGITS
     województwie
    0.66
     فريبيس
    0.49
    ypso
    0.43
    localctx
    0.42
     CreateTagHelper
    0.42
    rawDesc
    0.41
     chants
    0.40
    zug
    0.40
     عن
    0.39
    FirstResponder
    0.39
    Activations Density 0.014%

    No Known Activations