© 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. 95094
    Prev
    Next
    INDEX
    Explanations

    colon character

    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
     gese
    -0.59
    Define
    -0.58
    count
    -0.51
    IZON
    -0.50
    ology
    -0.50
    threshold
    -0.50
    Vaata
    -0.49
    ˈ
    -0.49
     fous
    -0.48
     gì
    -0.48
    POSITIVE LOGITS
    MigrationBuilder
    0.73
    invokeLater
    0.63
    oredCriteria
    0.61
     insuffisamment
    0.59
    WriteTagHelper
    0.59
    ंदीखरीदारी
    0.54
    AnimationsModule
    0.54
     IndexPath
    0.52
     DialogResult
    0.52
    SerializedSize
    0.52
    Activations Density 0.007%

    No Known Activations