© 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. 4-CLT-HP
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    at

    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
    MessageOf
    -0.98
     propOrder
    -0.94
     initComponents
    -0.82
     disambiguazione
    -0.81
    WithIOException
    -0.79
    AddTagHelper
    -0.78
     CreateTagHelper
    -0.75
    +#+#
    -0.73
    IsContent
    -0.73
     '\\;'
    -0.71
    POSITIVE LOGITS
    oob
    0.47
    羯
    0.46
    archiviato
    0.46
     Different
    0.45
     look
    0.45
     tick
    0.43
     tag
    0.43
     different
    0.42
     Right
    0.42
     cry
    0.42
    Activations Density 0.003%

    No Known Activations