© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44214
    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
    -2.67
    love
    -2.16
     Love
    -1.92
     LOVE
    -1.91
    Love
    -1.78
    LOVE
    -1.64
     loved
    -1.52
     loves
    -1.48
     adore
    -1.37
     hate
    -1.24
    POSITIVE LOGITS
     Majefty
    1.01
     pleaſure
    1.00
     Monfieur
    0.99
     Efq
    0.98
     Houſe
    0.98
     Shakspeare
    0.96
     houſe
    0.94
     purpoſe
    0.93
     greateſt
    0.91
     ſtate
    0.90
    Activations Density 0.210%

    No Known Activations