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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93863
    Prev
    Next
    INDEX
    Explanations

    expansion

    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
     expansion
    -1.24
     Expansion
    -1.05
     expanding
    -1.02
    expansion
    -1.01
    Expansion
    -0.96
     expansions
    -0.84
     expand
    -0.83
     Expanding
    -0.83
     expansión
    -0.81
    expanding
    -0.76
    POSITIVE LOGITS
    رشف
    0.71
     transfieras
    0.66
    Composable
    0.65
    IMPORTED
    0.61
    GEBURTSDATUM
    0.61
     المعرف
    0.59
    Autoritní
    0.59
    ticity
    0.59
     OFDb
    0.59
    :✨
    0.57
    Activations Density 0.217%

    No Known Activations