© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 75095
    Prev
    Next
    INDEX
    Explanations

    sand and calcium

    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
     typelib
    -0.76
     estekak
    -0.72
     الدولى
    -0.71
    featureID
    -0.70
     nahilalakip
    -0.67
     تضيفلها
    -0.66
    ⓧ
    -0.65
    MemoryWarning
    -0.62
     useCallback
    -0.61
    GraphicsUnit
    -0.61
    POSITIVE LOGITS
     sand
    0.69
     de
    0.66
     sands
    0.55
     salt
    0.54
     calcium
    0.54
     مشين
    0.53
     Calcium
    0.50
    Calcium
    0.50
    calcium
    0.50
     gravel
    0.49
    Activations Density 0.000%

    No Known Activations