© 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. 0-CLT-HP
    7. 97327
    Prev
    Next
    INDEX
    Explanations

    Laura

    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
    Laura
    -0.59
     conservative
    -0.59
    <tbody>
    -0.57
     Laura
    -0.56
    PARTIC
    -0.52
    yyj
    -0.52
    /**
    -0.51
    limard
    -0.50
    ط
    -0.48
    Cre
    -0.48
    POSITIVE LOGITS
    AutoScaleMode
    0.68
    NameInMap
    0.67
     GeoNames
    0.60
    complexContent
    0.57
    localctx
    0.56
    setVerticalGroup
    0.56
    Datuak
    0.55
    WebVitals
    0.54
     oprot
    0.54
    oneofs
    0.54
    Activations Density 1.598%

    No Known Activations