© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4025
    Prev
    Next
    INDEX
    Explanations

    smart

    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
     myſelf
    -0.70
     ainfi
    -0.67
     preuves
    -0.64
     enfans
    -0.61
     énergé
    -0.60
     mauvaises
    -0.60
     attentes
    -0.59
     préfé
    -0.59
     amitié
    -0.57
    MessageOf
    -0.57
    POSITIVE LOGITS
    watches
    0.59
    :+:
    0.57
    NOPQRST
    0.55
    AndroidJUnit
    0.54
    BufferException
    0.54
    TestingModule
    0.52
    migrationBuilder
    0.51
     showers
    0.48
    ware
    0.46
     الرياضيه
    0.46
    Activations Density 0.001%

    No Known Activations