© 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. 20-CLT-HP
    7. 74966
    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
     anthracite
    -0.59
    Personensuche
    -0.58
    InstanceState
    -0.58
     octave
    -0.57
    Surface
    -0.57
    NonQuery
    -0.57
    surface
    -0.56
    SURFACE
    -0.56
    éclairage
    -0.56
     Supra
    -0.56
    POSITIVE LOGITS
     EconPapers
    0.64
    ("")]
    0.58
     nahilalakip
    0.53
     four
    0.52
     FOUR
    0.50
     five
    0.50
     FIVE
    0.46
     Five
    0.46
     Four
    0.46
     fifty
    0.45
    Activations Density 0.003%

    No Known Activations