© 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. 1-CLT-HP
    7. 12323
    Prev
    Next
    INDEX
    Explanations

    deck

    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
     deck
    -1.28
     Deck
    -1.27
    Deck
    -1.18
    deck
    -1.18
     decks
    -1.09
     DECK
    -1.07
     Decks
    -1.01
    decks
    -0.97
     decking
    -0.94
    デッキ
    -0.61
    POSITIVE LOGITS
     AppColors
    0.51
     EconPapers
    0.50
    Jeografia
    0.50
    Javadoc
    0.48
     Насе
    0.48
    حوالہ
    0.48
    forRoot
    0.47
    Бахар
    0.45
    Imagin
    0.45
    তথ্যসূত্র
    0.44
    Activations Density 0.069%

    No Known Activations