© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2548
    Prev
    Next
    INDEX
    Explanations

    online articles/posts

    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
     AssemblyCulture
    -0.69
     <>",
    -0.68
    rungsseite
    -0.66
    Personensuche
    -0.63
    PerformLayout
    -0.57
     ModelExpression
    -0.57
    EndGlobalSection
    -0.55
    ItemBackground
    -0.51
    <bos>
    -0.51
    sizeCache
    -0.50
    POSITIVE LOGITS
    новништво
    0.68
     Audiodateien
    0.59
    átiles
    0.58
    corporated
    0.58
    показания
    0.57
    Formazione
    0.57
    voorbeeld
    0.54
    ברס
    0.54
    vician
    0.53
    gæ
    0.52
    Activations Density 0.004%

    No Known Activations