© 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. 92621
    Prev
    Next
    INDEX
    Explanations

    ki

    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
     via
    -0.82
    omaterial
    -0.56
     vía
    -0.56
    ortiment
    -0.52
    avoie
    -0.49
    ndag
    -0.49
     fermés
    -0.49
    RenderAtEndOf
    -0.48
     cuire
    -0.48
    たまた
    -0.47
    POSITIVE LOGITS
    RegistryLite
    0.80
     Majefty
    0.77
     reaſon
    0.75
     NSCoder
    0.75
     ſche
    0.69
     resourceCulture
    0.69
    ]='\
    0.68
     unſ
    0.66
     preſent
    0.66
     fubject
    0.66
    Activations Density 0.524%

    No Known Activations