© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72766
    Prev
    Next
    INDEX
    Explanations

    diverse subjects

    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
    complexType
    -0.87
    ècie
    -0.81
    EndContext
    -0.79
    Autoritní
    -0.74
     الرياضيه
    -0.72
     CascadeType
    -0.71
    oa̍t
    -0.69
    rungsseite
    -0.68
    /*---
    -0.68
     EconPapers
    -0.68
    POSITIVE LOGITS
     subjects
    0.62
     fre
    0.62
     sujets
    0.54
     subject
    0.52
    Subjects
    0.48
    subjects
    0.47
     Subjects
    0.47
    fre
    0.47
     free
    0.43
     موا
    0.41
    Activations Density 0.000%

    No Known Activations