© 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. 0-CLT-HP
    7. 93621
    Prev
    Next
    INDEX
    Explanations

    Th

    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
    ians
    -0.87
     Th
    -0.75
    ised
    -0.68
    Th
    -0.64
    iest
    -0.61
    ner
    -0.60
    ian
    -0.55
    eau
    -0.55
    i
    -0.55
    ized
    -0.54
    POSITIVE LOGITS
    +:+
    0.90
    TagMode
    0.84
     AssemblyTitle
    0.81
    MigrationBuilder
    0.80
    ScopeManager
    0.79
    GraphicsUnit
    0.77
     незавершена
    0.74
     Wikimédia
    0.74
    modelBuilder
    0.73
     **/
    0.73
    Activations Density 0.374%

    No Known Activations