© 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. 9180
    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
    -1.30
     Love
    -1.25
    Love
    -1.23
    love
    -1.13
     LOVE
    -1.04
    LOVE
    -0.98
     loved
    -0.81
     loving
    -0.75
     loves
    -0.73
     Loved
    -0.71
    POSITIVE LOGITS
    ]--;
    0.75
     تانيه
    0.73
    Autoritní
    0.66
     himo
    0.65
     Meksiku
    0.64
    ghold
    0.63
     createSlice
    0.62
     MediatR
    0.62
     autorytatywna
    0.62
    inafter
    0.62
    Activations Density 0.031%

    No Known Activations