© 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. 73628
    Prev
    Next
    INDEX
    Explanations

    Formal documents

    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
     GenerationType
    -0.57
    发表于
    -0.52
    ніципалі
    -0.48
    Autoritní
    -0.47
     وتسجيلات
    -0.47
    WireFormat
    -0.47
    ]<<"
    -0.47
     Ause
    -0.46
    chuga
    -0.46
     barges
    -0.46
    POSITIVE LOGITS
     الدولى
    0.56
    ReferenceEquals
    0.54
    Gleich
    0.48
    Beijo
    0.47
    istad
    0.47
    ništvo
    0.47
    getValueAt
    0.46
    السكان
    0.45
    ئي
    0.45
    substack
    0.45
    Activations Density 0.000%

    No Known Activations