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. 73941
    Prev
    Next
    INDEX
    Explanations

    random text 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
    AddTagHelper
    -0.80
    ftagPool
    -0.74
     betweenstory
    -0.73
    SharedDtor
    -0.70
     дописавши
    -0.69
    writeFieldEnd
    -0.68
    prüche
    -0.68
     चीज़ों
    -0.68
    StructEnd
    -0.66
    NewUrlParser
    -0.66
    POSITIVE LOGITS
    pon
    0.48
    Digitized
    0.42
    يكب
    0.41
    /*
    0.39
     alun
    0.38
    imdi
    0.38
    con
    0.37
    浮か
    0.35
    ken
    0.35
    ="#">
    0.35
    Activations Density 0.001%

    No Known Activations