© 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. 0-CLT-HP
    7. 41724
    Prev
    Next
    INDEX
    Explanations

    entitled

    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
     itſelf
    -0.95
    Geplaatst
    -0.89
    TypedDataSet
    -0.85
     referenties
    -0.82
     تانيه
    -0.82
    出版年
    -0.82
    MLLoader
    -0.81
     CreateTagHelper
    -0.79
    MethodManager
    -0.79
    DockStyle
    -0.78
    POSITIVE LOGITS
     are
    0.64
    ↵
    0.56
     '
    0.54
     were
    0.50
     the
    0.49
     follow
    0.49
     "
    0.48
     play
    0.47
     
    0.47
     great
    0.45
    Activations Density 0.404%

    No Known Activations