© 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. 45367
    Prev
    Next
    INDEX
    Explanations

    court, legal rulings

    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
    seamnă
    -0.59
    ful
    -0.52
     față
    -0.49
     Pública
    -0.48
     Constitucional
    -0.48
     regolare
    -0.47
    zköz
    -0.46
     knob
    -0.45
     mẽ
    -0.44
     liné
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.77
    rungsseite
    0.70
    UrlResolution
    0.67
    expandindo
    0.66
    SourceChecksum
    0.65
    $_['
    0.61
     незавершена
    0.61
     Référence
    0.59
    Carriera
    0.59
     ExecuteAsync
    0.59
    Activations Density 0.473%

    No Known Activations