© 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. 1-CLT-HP
    7. 10728
    Prev
    Next
    INDEX
    Explanations

    Upper

    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
    baomidou
    -0.47
    ̸
    -0.46
    Напомним
    -0.44
    velles
    -0.43
     usah
    -0.42
     труда
    -0.42
    essi
    -0.41
     sie
    -0.41
     nung
    -0.41
    ñador
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.84
    tagHelperRunner
    0.79
     nakalista
    0.74
     الحره
    0.72
    ⓧ
    0.72
    ViewImports
    0.71
    msgTypes
    0.70
    mybatisplus
    0.69
    脚注の使い方
    0.68
     AssemblyProduct
    0.68
    Activations Density 0.014%

    No Known Activations