© 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. 20-CLT-HP
    7. 74646
    Prev
    Next
    INDEX
    Explanations

    Code and licensing

    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
    PerformLayout
    -0.47
     SwiftUI
    -0.45
    脚注の使い方
    -0.41
     TAMBÉM
    -0.38
    SequentialGroup
    -0.38
     ChromeDriver
    -0.38
     viewDidLoad
    -0.38
     Skye
    -0.36
     AssemblyTitle
    -0.35
    ritsar
    -0.35
    POSITIVE LOGITS
    oredCriteria
    0.84
    feelings
    0.68
    loving
    0.67
    lessons
    0.60
     createState
    0.60
     feelings
    0.58
    Autoritní
    0.58
    sense
    0.58
     value
    0.57
    winning
    0.57
    Activations Density 0.002%

    No Known Activations