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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12621
    Prev
    Next
    INDEX
    Explanations

    bays

    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
     bays
    -1.22
     Bays
    -1.05
     bay
    -0.62
    IsMutable
    -0.57
     NSCoder
    -0.56
     Conquer
    -0.54
     kaikki
    -0.51
    ArrowToggle
    -0.51
     Taro
    -0.50
     Paradis
    -0.49
    POSITIVE LOGITS
    ides
    0.63
    MultipartFile
    0.54
    发表于
    0.52
    lines
    0.52
    tagHelper
    0.49
    ding
    0.49
    iness
    0.48
    hed
    0.47
    assium
    0.47
    CodedInputStream
    0.47
    Activations Density 0.004%

    No Known Activations