© 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. 0-CLT-HP
    7. 43796
    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
     these
    -0.84
     These
    -0.57
    these
    -0.52
    These
    -0.49
     pageContext
    -0.49
    seer
    -0.48
     prior
    -0.47
     questi
    -0.47
     THESE
    -0.46
    peteer
    -0.45
    POSITIVE LOGITS
    TagMode
    0.95
    ंदीखरीदारी
    0.84
     bezeichneter
    0.78
    Statics
    0.66
    principalTable
    0.65
    ⓧ
    0.62
    وأضاف
    0.62
     незавершена
    0.62
    ########.
    0.60
     насељу
    0.60
    Activations Density 1.724%

    No Known Activations