© 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. 5-CLT-HP
    7. 95123
    Prev
    Next
    INDEX
    Explanations

    more comparative statements

    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
    RefNanny
    -0.79
     propOrder
    -0.66
    WebControls
    -0.66
     AssemblyProduct
    -0.65
     EconPapers
    -0.63
     CreateTagHelper
    -0.63
     StatelessWidget
    -0.63
     ElementRef
    -0.62
    DeleteCommand
    -0.62
    ')):
    -0.61
    POSITIVE LOGITS
    like
    0.50
    Unlike
    0.50
    フィシャル
    0.48
     comigo
    0.48
    Like
    0.47
    ZZA
    0.47
    iose
    0.47
     varandra
    0.46
     unlike
    0.46
    Lähteet
    0.45
    Activations Density 0.002%

    No Known Activations