© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40307
    Prev
    Next
    INDEX
    Explanations

    tyranny

    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
    es
    -0.69
    s
    -0.69
    o
    -0.68
     fédé
    -0.65
    ly
    -0.64
    n
    -0.63
     toxin
    -0.62
     traditionnels
    -0.62
    t
    -0.60
    m
    -0.60
    POSITIVE LOGITS
     useSelector
    0.72
    awtextra
    0.68
    ]")]
    0.68
    andExpect
    0.66
     useAppContext
    0.64
     BufferedReader
    0.63
     onCancelled
    0.61
    脚注の使い方
    0.60
    SuppressMessage
    0.59
    orElseThrow
    0.59
    Activations Density 0.100%

    No Known Activations