© 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. 42416
    Prev
    Next
    INDEX
    Explanations

    love

    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
     love
    -1.99
    love
    -1.87
    Love
    -1.78
     Love
    -1.77
     loving
    -1.65
     LOVE
    -1.55
    LOVE
    -1.48
     loves
    -1.40
     LOV
    -1.38
     Loving
    -1.33
    POSITIVE LOGITS
    MetaType
    0.81
    oredCriteria
    0.74
    FormTagHelper
    0.73
    InstrumentedTest
    0.73
    AccessorTable
    0.66
    ashions
    0.65
    NameInMap
    0.62
    WriteBarrier
    0.62
     IDisposable
    0.62
    domada
    0.61
    Activations Density 0.223%

    No Known Activations