© 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. 321
    Prev
    Next
    INDEX
    Explanations

    technical/scientific text snippets

    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
     helical
    -0.59
    Kaieteur
    -0.49
     phenomenon
    -0.49
     fellowship
    -0.46
     curled
    -0.46
     yi
    -0.45
    hi
    -0.44
    ("</
    -0.44
     gap
    -0.43
     Fei
    -0.42
    POSITIVE LOGITS
    FormTagHelper
    0.84
     AssemblyCulture
    0.82
     initComponents
    0.79
    WithIOException
    0.77
    DoubleQuotes
    0.76
     AppCompatTheme
    0.75
    featureID
    0.72
    webElementXpaths
    0.71
    المناصب
    0.70
     resourceCulture
    0.69
    Activations Density 0.129%

    No Known Activations