© 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. 97473
    Prev
    Next
    INDEX
    Explanations

    biosynthesis

    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
     supplement
    -1.00
    supplement
    -0.98
     supplementation
    -0.95
     supplé
    -0.94
     doInBackground
    -0.91
     IBOutlet
    -0.90
    Supplement
    -0.89
     supplementing
    -0.88
    sidemargin
    -0.88
     Supplement
    -0.88
    POSITIVE LOGITS
    ↵↵
    0.58
    -
    0.54
    ↵
    0.50
    to
    0.50
    t
    0.49
    2
    0.47
     system
    0.46
     products
    0.45
    tor
    0.44
    tal
    0.44
    Activations Density 0.094%

    No Known Activations