© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4056
    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
     فريبيس
    -0.81
     ModelExpression
    -0.75
     CreateTagHelper
    -0.74
     '\\;'
    -0.74
     handleMessage
    -0.68
    ])))
    -0.64
     CURLOPT
    -0.64
    WarningLevel
    -0.61
    ])):
    -0.60
     &___
    -0.59
    POSITIVE LOGITS
     next
    0.69
     final
    0.64
    initializeApp
    0.55
     last
    0.55
    next
    0.53
    final
    0.52
    udesta
    0.50
     Enfin
    0.50
     laatste
    0.49
     fubject
    0.49
    Activations Density 0.000%

    No Known Activations