© 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. 38716
    Prev
    Next
    INDEX
    Explanations

    varied code 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
     in
    -0.63
     via
    -0.62
     his
    -0.59
     within
    -0.59
     of
    -0.58
     Her
    -0.57
     db
    -0.57
    eria
    -0.56
     to
    -0.55
     int
    -0.54
    POSITIVE LOGITS
    <bos>
    1.04
     Theſe
    0.84
     stället
    0.81
    ChromeDriver
    0.75
     varandra
    0.74
    styleType
    0.74
     Chriftian
    0.73
     Shakspeare
    0.73
     mourut
    0.72
     Efq
    0.72
    Activations Density 0.076%

    No Known Activations