© 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. 1-CLT-HP
    7. 15048
    Prev
    Next
    INDEX
    Explanations

    loading

    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
     treasure
    -0.55
     дописавши
    -0.54
     Treasure
    -0.54
    queryInterface
    -0.51
    டிய
    -0.51
    ?,?,
    -0.50
     Treasures
    -0.50
     privées
    -0.50
     faisaient
    -0.49
    IVEREF
    -0.49
    POSITIVE LOGITS
    styleType
    0.76
    bootstrapcdn
    0.59
    PyExc
    0.57
     تضيفلها
    0.56
     Lisbon
    0.52
     AssemblyProduct
    0.51
    som
    0.50
    e
    0.50
     GoogleFonts
    0.50
     InputDecoration
    0.50
    Activations Density 0.017%

    No Known Activations