© 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. 2146
    Prev
    Next
    INDEX
    Explanations

    subtraction

    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
     AssemblyTitle
    -0.66
    ilent
    -0.49
     Niv
    -0.48
    permitAll
    -0.47
    omeness
    -0.47
    illée
    -0.47
    fillna
    -0.46
     percolation
    -0.46
    genomen
    -0.46
    letterSpacing
    -0.46
    POSITIVE LOGITS
    PerformLayout
    0.74
    Portály
    0.63
     ExecuteAsync
    0.62
    ंदीखरीदारी
    0.60
    Биография
    0.54
    MessageTagHelper
    0.52
    InputTagHelper
    0.51
    GeneratedValue
    0.51
    出版年
    0.50
    bootstrapcdn
    0.50
    Activations Density 0.013%

    No Known Activations