© 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. 3543
    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
     defaultstate
    -0.57
     мәгълү
    -0.47
    matchCondition
    -0.46
    மா
    -0.43
    zung
    -0.41
    nella
    -0.41
    borderSide
    -0.41
     myself
    -0.41
     privilegi
    -0.41
    merate
    -0.40
    POSITIVE LOGITS
     ligiloj
    0.81
     صوتيه
    0.77
    harusnya
    0.73
    AutoScale
    0.64
     незавершена
    0.62
     propOrder
    0.61
     副本
    0.60
     Wikiseite
    0.57
    tidaknya
    0.56
     Мексичка
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.