© 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. 1228
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     TextInputType
    -0.49
     lateinit
    -0.46
     NSCoder
    -0.45
     createContext
    -0.43
    didSet
    -0.43
     Inflation
    -0.42
    नलिखित
    -0.42
    География
    -0.42
     sentito
    -0.40
    createCanvas
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.78
    parsedMessage
    0.73
    protoc
    0.69
     EconPapers
    0.64
     StatefulWidget
    0.61
    phite
    0.60
     '\\;'
    0.60
     allAfrica
    0.59
    AutoScaleMode
    0.59
    </b>
    0.57
    Activations Density 0.016%

    No Known Activations