© 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. 94258
    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
    ControllerAdvice
    -0.64
    脚注の使い方
    -0.63
     étoient
    -0.62
     fondamentali
    -0.62
    ніципалі
    -0.62
     consultato
    -0.62
     fondament
    -0.61
    Aiheesta
    -0.60
     fundamentales
    -0.60
     noires
    -0.59
    POSITIVE LOGITS
    anine
    0.50
    otho
    0.49
    taxia
    0.49
     crotch
    0.48
    calipsis
    0.47
    醐
    0.46
     savor
    0.45
    ishable
    0.44
    ołnier
    0.44
    vena
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.