© 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. 0-CLT-HP
    7. 40094
    Prev
    Next
    INDEX
    Explanations

    hold

    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
     hold
    -2.16
     holds
    -1.97
     holding
    -1.96
     held
    -1.95
    hold
    -1.87
     Hold
    -1.87
    Hold
    -1.84
     HOLD
    -1.79
    Holding
    -1.78
    holding
    -1.76
    POSITIVE LOGITS
    IndentedString
    0.54
     whereof
    0.52
    newswire
    0.52
    السكان
    0.50
     Agreed
    0.50
    XmlEnum
    0.50
    lägen
    0.50
     authorship
    0.49
     taxed
    0.49
    ыгана
    0.49
    Activations Density 0.102%

    No Known Activations