© 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. 5-CLT-HP
    4. 96600
    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
    StructEnd
    -0.56
     some
    -0.52
     last
    -0.52
    UniformLocation
    -0.50
     none
    -0.49
    FTFY
    -0.49
    SizeMode
    -0.48
    Diweddarwch
    -0.48
    fromCharCode
    -0.47
     on
    -0.47
    POSITIVE LOGITS
     auffi
    0.61
    Sit
    0.60
     ujednoznacz
    0.60
     falsa
    0.58
     gainera
    0.57
     FURTHER
    0.57
    tront
    0.56
     Pregnant
    0.55
    Further
    0.54
     Chairs
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.