© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    Spl

    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
    ########.
    -0.79
     مرئيه
    -0.77
    RenderAtEndOf
    -0.76
    UnusedPrivate
    -0.75
     CreateTagHelper
    -0.74
    ViewFeatures
    -0.73
    
    -0.71
    InjectAttribute
    -0.70
    ChildScrollView
    -0.68
     straw
    -0.68
    POSITIVE LOGITS
    atter
    0.53
     but
    0.52
     al
    0.52
     imp
    0.49
    attered
    0.49
     and
    0.48
     plan
    0.47
     honor
    0.46
    ItemBackground
    0.46
    liegen
    0.45
    Activations Density 0.595%

    No Known Activations