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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40052
    Prev
    Next
    INDEX
    Explanations

    ")]"

    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
    tableFuture
    -0.54
    ViewInit
    -0.52
     fermée
    -0.52
    )]
    -0.51
    StreetMap
    -0.50
     lumineuse
    -0.49
     viață
    -0.49
    ̚
    -0.49
    IntoConstraints
    -0.48
    tagHelper
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.67
     kasarigan
    0.62
     للمعارف
    0.59
    }}.
    0.57
    libft
    0.56
     AssemblyProduct
    0.55
    Diweddarwch
    0.55
    agisse
    0.54
     linkovi
    0.52
    :✨
    0.52
    Activations Density 0.071%

    No Known Activations