© 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. 5-CLT-HP
    7. 93979
    Prev
    Next
    INDEX
    Explanations

    settlement

    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
     confidential
    -0.82
     private
    -0.67
     privately
    -0.64
     Confidential
    -0.61
     openly
    -0.61
     secret
    -0.61
    addPreferredGap
    -0.60
     publicly
    -0.59
    🤫
    -0.56
     unofficial
    -0.55
    POSITIVE LOGITS
    +#+#
    0.82
     estekak
    0.72
    <bos>
    0.70
    DECREF
    0.56
    richTextPanel
    0.56
    الإنجليزية
    0.55
    सन्दर्भ
    0.54
    URLException
    0.53
    تقاوى
    0.51
    XMLSchema
    0.50
    Activations Density 0.007%

    No Known Activations