© 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. 96670
    Prev
    Next
    INDEX
    Explanations

    Document excerpts

    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
    anmoins
    -0.64
    StructEnd
    -0.62
    ChildScrollView
    -0.57
    WriteBarrier
    -0.57
    ButtonModule
    -0.56
    ogia
    -0.55
     setuptools
    -0.55
     صوتيه
    -0.55
    KURZBESCHREIBUNG
    -0.54
     SDLK
    -0.54
    POSITIVE LOGITS
     pages
    0.74
    pages
    0.60
     hours
    0.53
     bibliographical
    0.51
    Pages
    0.51
     slides
    0.50
     page
    0.49
    Zalety
    0.47
    defendant
    0.47
     pagina
    0.47
    Activations Density 0.001%

    No Known Activations