Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74240
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
    CloseOperation
    -0.60
    /*
    -0.59
     '\\;'
    -0.54
    cèse
    -0.52
     ahead
    -0.52
    Искәрмәләр
    -0.51
     kaarangay
    -0.51
     lenker
    -0.50
     ISNI
    -0.49
     NSCoder
    -0.49
    POSITIVE LOGITS
     it
    2.11
    It
    1.26
     It
    1.15
    it
    1.13
    它
    1.02
    มัน
    0.96
     nó
    0.90
     оно
    0.85
     itt
    0.81
     IT
    0.77
    Activations Density 0.000%

    No Known Activations