© 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. 1-CLT-HP
    7. 914
    Prev
    Next
    INDEX
    Explanations

    lean

    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
    lean
    -1.16
    leans
    -0.79
    LEAN
    -0.73
    Lean
    -0.68
     lean
    -0.63
     leaned
    -0.57
    leaner
    -0.57
    leaning
    -0.53
     leaning
    -0.52
     Lean
    -0.50
    POSITIVE LOGITS
     дописавши
    0.83
     autorytatywna
    0.75
     Wiktionnaire
    0.69
    expandindo
    0.67
     clots
    0.65
     clot
    0.65
     виправивши
    0.63
     الحره
    0.61
    \{\\
    0.58
    Effort
    0.57
    Activations Density 0.464%

    No Known Activations