© 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. 97462
    Prev
    Next
    INDEX
    Explanations

    loving

    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
    Loving
    -0.79
     Loving
    -0.72
     lose
    -0.71
     loving
    -0.69
     Lose
    -0.63
    loving
    -0.62
     twice
    -0.61
    Lose
    -0.60
     loses
    -0.57
     Protección
    -0.55
    POSITIVE LOGITS
    ities
    0.75
    ly
    0.67
     étrangère
    0.65
    edly
    0.63
    pendientes
    0.61
    NÍ
    0.61
     Tivoli
    0.59
     diagonals
    0.59
     ARXIV
    0.59
    ality
    0.58
    Activations Density 0.210%

    No Known Activations