© 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. 20-CLT-HP
    7. 74692
    Prev
    Next
    INDEX
    Explanations

    Code/web-page related

    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
     betweenstory
    -0.76
     архивлан
    -0.71
     Савезне
    -0.71
    XtraReports
    -0.65
     مرئيه
    -0.63
    Hochspringen
    -0.61
     '\\;'
    -0.61
    protoc
    -0.60
    ้งาน
    -0.59
    تفصیلات
    -0.59
    POSITIVE LOGITS
    DockStyle
    0.53
    דרה
    0.46
     election
    0.44
    ãy
    0.43
     administration
    0.43
    мость
    0.42
     campaign
    0.41
    ByDefault
    0.41
    enburg
    0.41
     CreateTagHelper
    0.40
    Activations Density 0.000%

    No Known Activations