© 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. 1-CLT-HP
    7. 13101
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
     resourceCulture
    -1.06
     EconPapers
    -0.91
    webElementGuid
    -0.85
    mybatisplus
    -0.84
    Попис
    -0.82
    InstrumentedTest
    -0.81
     disambiguazione
    -0.79
     Мексичка
    -0.79
    AndEndTag
    -0.76
    #+#
    -0.74
    POSITIVE LOGITS
    [
    0.65
     simply
    0.61
     
    0.58
     very
    0.57
     in
    0.53
     AssemblyTitle
    0.53
     perhaps
    0.53
     only
    0.52
     often
    0.52
     similarly
    0.51
    Activations Density 0.057%

    No Known Activations