© 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. 20-CLT-HP
    7. 74840
    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
    onAttach
    -0.54
    esModule
    -0.52
    consulté
    -0.50
    Chham
    -0.50
     dévelo
    -0.50
    extAlignment
    -0.49
     correctes
    -0.49
    uality
    -0.48
    umumkan
    -0.48
     cardiaque
    -0.48
    POSITIVE LOGITS
    Бахар
    0.61
     ModelExpression
    0.52
     TAMBÉM
    0.51
     Pop
    0.49
    wezig
    0.48
    Rhestr
    0.47
    SharedCtor
    0.47
     iconTwitter
    0.47
     trust
    0.47
     rab
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.