© 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. 38466
    Prev
    Next
    INDEX
    Explanations

    of

    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
     
    -0.70
     a
    -0.59
     CascadeType
    -0.55
     but
    -0.52
    czer
    -0.49
    clf
    -0.49
     all
    -0.48
     I
    -0.48
     an
    -0.48
     lot
    -0.47
    POSITIVE LOGITS
     nahilalakip
    0.82
     MainAxisSize
    0.82
     AssemblyProduct
    0.77
     itſelf
    0.74
    Hozzáférés
    0.72
     архивлан
    0.71
     дописавши
    0.71
    OCCURRED
    0.68
    InjectAttribute
    0.68
    UnknownFields
    0.68
    Activations Density 0.551%

    No Known Activations