© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96253
    Prev
    Next
    INDEX
    Explanations

    finding information

    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
    setupUi
    -0.66
    WebElementEntity
    -0.63
    WindowConstants
    -0.63
    Personendaten
    -0.62
     wikipagina
    -0.62
    kháu
    -0.59
    ImageContext
    -0.58
    Portale
    -0.58
     genitori
    -0.57
    MigrationBuilder
    -0.57
    POSITIVE LOGITS
     more
    1.05
     if
    0.88
     More
    0.77
     Which
    0.65
     lebih
    0.63
     If
    0.62
     How
    0.62
     further
    0.61
    more
    0.60
     how
    0.59
    Activations Density 0.002%

    No Known Activations