© 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. 91008
    Prev
    Next
    INDEX
    Explanations

    term

    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
    Term
    -0.98
     term
    -0.96
     Term
    -0.89
    term
    -0.82
    TERM
    -0.79
     terme
    -0.74
     TERM
    -0.68
    bium
    -0.68
    Terms
    -0.65
    terms
    -0.64
    POSITIVE LOGITS
    Referències
    0.90
    AndEndTag
    0.87
     незавершена
    0.84
     AssemblyCulture
    0.82
    ViewFeatures
    0.81
    Atsauces
    0.71
    IUrlHelper
    0.70
    AsUp
    0.69
     <=",
    0.68
    IonicModule
    0.68
    Activations Density 0.097%

    No Known Activations