© 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. 40454
    Prev
    Next
    INDEX
    Explanations

    fraction

    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
     separated
    -1.08
     separation
    -1.06
     sépar
    -1.06
    union
    -0.97
     separations
    -0.93
     Separ
    -0.90
     separación
    -0.89
     séparation
    -0.88
     separating
    -0.88
     unity
    -0.83
    POSITIVE LOGITS
    ArrowToggle
    0.57
    aries
    0.56
    ized
    0.52
    arians
    0.52
    formin
    0.50
    riwal
    0.50
    ultor
    0.50
    ists
    0.49
    hedrals
    0.49
    emia
    0.49
    Activations Density 0.131%

    No Known Activations