© 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. 38504
    Prev
    Next
    INDEX
    Explanations

    due

    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
     due
    -1.40
     Due
    -1.10
    due
    -1.09
    Due
    -1.08
     devido
    -1.02
     debido
    -1.01
     DUE
    -0.88
    DUE
    -0.85
     aufgrund
    -0.64
    由于
    -0.60
    POSITIVE LOGITS
     GenerationType
    0.85
     Monfieur
    0.82
     AppModule
    0.79
     GetEnumerator
    0.77
     Theſe
    0.75
    MessageOf
    0.75
    itinéraire
    0.74
    tagext
    0.74
    ">//
    0.71
     Mahomet
    0.69
    Activations Density 0.063%

    No Known Activations