© 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. 4-CLT-HP
    7. 2414
    Prev
    Next
    INDEX
    Explanations

    Scientific reports/articles

    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
     heti
    -0.52
     desconhe
    -0.51
     délib
    -0.46
    .
    -0.46
     comigo
    -0.46
     vyst
    -0.43
     lèvres
    -0.43
     aucun
    -0.43
     primeiras
    -0.41
    刁
    -0.41
    POSITIVE LOGITS
    ьаж
    0.88
    ValueStyle
    0.87
    
    0.81
     архивлан
    0.80
    expandindo
    0.68
    XMLSchema
    0.68
     Administrativna
    0.68
     >=",
    0.66
     дописавши
    0.65
     CURIAM
    0.64
    Activations Density 0.014%

    No Known Activations