© 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. 4-CLT-HP
    7. 4998
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
     AssemblyProduct
    -0.72
     AttributeSet
    -0.61
    ✨:
    -0.55
    aronder
    -0.51
    IsMutable
    -0.50
    shed
    -0.50
     MotionEvent
    -0.49
    Lyric
    -0.49
     shed
    -0.49
    </thead>
    -0.49
    POSITIVE LOGITS
    Билгалдахарш
    0.69
    MessageOf
    0.52
     unknownFields
    0.50
     Society
    0.50
    róleo
    0.48
    zköz
    0.47
    кумулятор
    0.46
     woorden
    0.46
     looms
    0.46
    SEPARATOR
    0.45
    Activations Density 0.004%

    No Known Activations