© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5131
    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
     solving
    -0.51
     solution
    -0.50
     :
    -0.49
    jgl
    -0.48
     engineers
    -0.47
     Solution
    -0.47
     job
    -0.46
     designer
    -0.45
     customer
    -0.45
     task
    -0.44
    POSITIVE LOGITS
    
    0.65
     hausse
    0.63
     ativos
    0.61
    ContextHolder
    0.60
     række
    0.60
     croire
    0.60
     teneur
    0.59
     inférieure
    0.59
     iprot
    0.59
     ativa
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.