© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76275
    Prev
    Next
    INDEX
    Explanations

    proteins and genes

    np_max-act-logits · 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
    jsxFileName
    -0.79
     polymers
    -0.78
    SharedCtor
    -0.77
     currencies
    -0.75
     devices
    -0.75
     toys
    -0.74
     languages
    -0.74
     muscles
    -0.73
     hormones
    -0.73
     instruments
    -0.73
    POSITIVE LOGITS
     protein
    0.77
     gene
    0.59
     enzyme
    0.50
    ingos
    0.49
     compound
    0.47
     molecule
    0.44
     receptor
    0.41
     antibody
    0.41
     section
    0.40
     substance
    0.40
    Activations Density 0.013%

    No Known Activations