© 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. 90818
    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
    SequentialGroup
    -0.56
     Cataloging
    -0.54
     ſch
    -0.52
    Controllo
    -0.52
     Jurí
    -0.52
     Económica
    -0.49
     Shakspeare
    -0.48
    tagHelperRunner
    -0.48
    /*---
    -0.47
     Aler
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.68
     cherchés
    0.65
    Rüyada
    0.65
    MockMvc
    0.64
    ])));
    0.60
    wyr
    0.55
    SpringBootTest
    0.54
    zane
    0.54
    FRAME
    0.54
    abancı
    0.53
    Activations Density 1.694%

    No Known Activations