© 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. 94994
    Prev
    Next
    INDEX
    Explanations

    performers

    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
    asional
    -0.57
     had
    -0.50
     ujednoznacz
    -0.49
     betweenstory
    -0.47
    rigu
    -0.47
     became
    -0.47
     وتسجيلات
    -0.47
    />";
    -0.47
     viewDidLoad
    -0.46
    RTEE
    -0.46
    POSITIVE LOGITS
     intent
    0.62
    ksesta
    0.57
     fuite
    0.57
    typeorm
    0.56
     leçon
    0.55
     Godt
    0.54
     strå
    0.54
     Intent
    0.54
     useAppContext
    0.54
     mannen
    0.53
    Activations Density 0.001%

    No Known Activations