© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74846
    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
     myſelf
    -0.88
     itſelf
    -0.85
     Efq
    -0.84
     Chriftian
    -0.82
     Theſe
    -0.78
     sumpay
    -0.77
     étoit
    -0.76
    oneofs
    -0.75
    клопе
    -0.75
     auroit
    -0.74
    POSITIVE LOGITS
     an
    0.85
    an
    0.70
     “
    0.68
     "
    0.68
    -
    0.67
     :
    0.63
    :
    0.59
     ‘
    0.58
     An
    0.56
    .
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.