© 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. 94838
    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
    PerformLayout
    -0.94
     nahilalakip
    -0.93
    Билгалдахарш
    -0.92
    WaitGroup
    -0.90
    AndEndTag
    -0.89
    MemoryWarning
    -0.85
    StoryboardSegue
    -0.85
    GraphicsUnit
    -0.84
    sizeCache
    -0.84
     AssemblyCompany
    -0.82
    POSITIVE LOGITS
    bir
    0.51
    bor
    0.44
    zepte
    0.43
     his
    0.43
    his
    0.42
     maj
    0.42
    bora
    0.41
    Flex
    0.41
     facture
    0.40
    AccessControl
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.