© 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. 20-CLT-HP
    7. 73684
    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
    elemField
    -0.77
     AssemblyCulture
    -0.76
     للمعارف
    -0.75
    rungsseite
    -0.71
    EDEFAULT
    -0.70
     snippetHide
    -0.70
    ⓧ
    -0.68
     дописавши
    -0.68
     OFDb
    -0.67
    istoitu
    -0.66
    POSITIVE LOGITS
     Timur
    0.40
     owe
    0.40
     PHR
    0.40
    уд
    0.39
    anız
    0.38
    Sua
    0.37
     μην
    0.37
     lese
    0.37
     Teng
    0.36
     oublier
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.