© 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. 0-CLT-HP
    7. 43872
    Prev
    Next
    INDEX
    Explanations

    page/pages

    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
    page
    -1.78
     pages
    -1.67
     page
    -1.66
    pages
    -1.63
    Pages
    -1.47
     Pages
    -1.43
    Page
    -1.42
     Page
    -1.27
    PAGE
    -1.25
     PAGE
    -1.20
    POSITIVE LOGITS
    TemporalType
    0.84
    GenerationType
    0.80
     تكبرها
    0.77
    StoryboardSegue
    0.76
    ]")]
    0.76
     myſelf
    0.72
     contextLoads
    0.71
    endphp
    0.71
    FormTagHelper
    0.71
    NUMX
    0.71
    Activations Density 0.134%

    No Known Activations