© 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. 75918
    Prev
    Next
    INDEX
    Explanations

    Art, culture, specialized vocabulary

    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
    ArgsConstructor
    -0.85
    RegistryLite
    -0.60
    ///</
    -0.59
     OnInit
    -0.56
     Motta
    -0.55
    жели
    -0.54
     Vikipedi
    -0.53
    өз
    -0.53
    beo
    -0.52
    nościo
    -0.52
    POSITIVE LOGITS
     AssemblyTitle
    0.58
     незавершена
    0.55
     presidencial
    0.54
    Skocz
    0.52
     humaines
    0.48
    didSet
    0.47
     diken
    0.47
    WebElementEntity
    0.46
     religieuses
    0.45
     prochaines
    0.44
    Activations Density 0.000%

    No Known Activations