© 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. 4-CLT-HP
    7. 1103
    Prev
    Next
    INDEX
    Explanations

    biographies

    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
    <bos>
    -0.91
    AndEndTag
    -0.57
    mybatisplus
    -0.54
    Espèce
    -0.53
    //
    -0.50
    matchCondition
    -0.50
    öö
    -0.50
     yapılan
    -0.49
     ikkje
    -0.49
     født
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.78
    Personendaten
    0.52
    tableFuture
    0.52
     resourceCulture
    0.50
     وتسجيلات
    0.49
    GEBURTSDATUM
    0.49
    脚注の使い方
    0.47
    EndProject
    0.46
    VersionUID
    0.46
     defaultstate
    0.45
    Activations Density 0.024%

    No Known Activations