© 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. 93969
    Prev
    Next
    INDEX
    Explanations

    their

    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
     reserved
    -0.62
     special
    -0.56
    Reserved
    -0.53
     réservé
    -0.53
     vorbehalten
    -0.51
     RESERVED
    -0.50
     Reserved
    -0.50
     reserve
    -0.45
    reserved
    -0.45
     Shall
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.81
    endphp
    0.79
    Vaata
    0.77
    NameInMap
    0.77
    OGND
    0.75
     dAtA
    0.75
    Rhestr
    0.72
    تقاوى
    0.72
    ItemBackground
    0.72
    ंदीखरीदारी
    0.71
    Activations Density 0.003%

    No Known Activations