© 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. 0-CLT-HP
    4. 1496
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical descriptions

    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
     while
    -1.31
    while
    -1.06
     While
    -1.05
    While
    -0.97
     mientras
    -0.90
     WHILE
    -0.88
     mentre
    -0.84
     enquanto
    -0.82
     بينما
    -0.77
     French
    -0.73
    POSITIVE LOGITS
    ImageContext
    0.75
     Wiktionnaire
    0.74
    endphp
    0.71
    ScopeManager
    0.63
    VolleyError
    0.60
     recognising
    0.60
    hloromethane
    0.58
     sqlSession
    0.57
    enumi
    0.55
    ptonshire
    0.55
    Activations Density 0.179%

    No Known Activations