© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1126
    Prev
    Next
    INDEX
    Explanations

    contradiction conjunctions

    np_max-act · gemini-2.0-flash
    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
    ItemBackground
    -0.69
     CreateTagHelper
    -0.61
     propOrder
    -0.57
    ThroughAttribute
    -0.56
    oneofs
    -0.52
    Personendaten
    -0.51
    WebElementEntity
    -0.48
     disagreement
    -0.46
    ImageContext
    -0.46
     buck
    -0.46
    POSITIVE LOGITS
     оригіналу
    0.73
     Recognizing
    0.66
     recognising
    0.66
     Recogn
    0.65
    enumii
    0.63
     recognizing
    0.63
     he
    0.61
     recognises
    0.60
     recognizes
    0.58
     fijn
    0.57
    Activations Density 0.003%

    No Known Activations