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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14058
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to energy consumption and efficiency

    oai_token-act-pair · gemini-2.0-flash

    energy efficiency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AttributeSet
    -0.78
    __':
    
    -0.65
    __':
    -0.65
    وگرافی
    -0.63
    CloseOperation
    -0.61
    Portail
    -0.59
    ography
    -0.57
     Dage
    -0.56
     LoggerFactory
    -0.56
    ImageContext
    -0.55
    POSITIVE LOGITS
     effective
    1.04
    Effective
    1.01
    effec
    0.95
     eff
    0.94
     effec
    0.93
    EFFECT
    0.91
     efficiency
    0.90
     efficient
    0.89
     Effective
    0.88
    effective
    0.88
    Activations Density 1.776%

    No Known Activations