Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73825
    Prev
    Next
    INDEX
    Explanations

    scientific assays

    np_max-act-logits · 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
     AssemblyCompany
    -0.77
     GenerationType
    -0.70
     AssemblyCulture
    -0.68
    发表于
    -0.66
    TypedDataSet
    -0.65
    évaluateur
    -0.61
    AutoSize
    -0.59
    angsaan
    -0.59
     mẽ
    -0.58
    WriteTagHelper
    -0.57
    POSITIVE LOGITS
     doble
    0.49
    double
    0.44
     double
    0.43
     diing
    0.42
    tvguidetime
    0.41
     doppio
    0.40
    zyme
    0.40
    чительно
    0.39
     Doub
    0.38
    rag
    0.38
    Activations Density 0.002%

    No Known Activations