© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74906
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    BoxShadow
    -0.62
     aufzu
    -0.60
    Portale
    -0.60
     становника
    -0.59
    بوابة
    -0.53
    audiovisuel
    -0.51
    Expedia
    -0.49
     الدولى
    -0.49
    Venta
    -0.47
     Telling
    -0.47
    POSITIVE LOGITS
     resourceCulture
    0.79
    AnchorTagHelper
    0.69
    msgTypes
    0.61
     "..\..\..\
    0.61
    NameInMap
    0.59
    MessageTagHelper
    0.58
    ContentAsync
    0.58
     prime
    0.58
     gna
    0.57
     ground
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.