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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75402
    Prev
    Next
    INDEX
    Explanations

    bin

    np_max-act-logits · 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
    Viitteet
    -0.61
    
    -0.61
    日閲覧
    -0.56
     الرياضيه
    -0.53
    Tikang
    -0.50
    __(/*!
    -0.50
    脚注の使い方
    -0.49
    SpringBootTest
    -0.47
     scorso
    -0.46
    ub
    -0.46
    POSITIVE LOGITS
     and
    0.70
     للاسماء
    0.67
     solid
    0.62
    solid
    0.59
     acts
    0.58
     SOLID
    0.56
    Solid
    0.56
     Octo
    0.56
     plus
    0.54
    acts
    0.54
    Activations Density 0.001%

    No Known Activations