© 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. 1731
    Prev
    Next
    INDEX
    Explanations

    Non-standard characters

    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
     GenerationType
    -0.61
    featureID
    -0.59
    mybatisplus
    -0.58
     extensão
    -0.58
    Ārējās
    -0.58
    stellung
    -0.57
    IonicModule
    -0.56
    esteld
    -0.56
    XMLSchema
    -0.56
    strophy
    -0.54
    POSITIVE LOGITS
     itſelf
    0.68
     Monfieur
    0.63
     Eſ
    0.63
     iſt
    0.61
     متعلقه
    0.59
     Perce
    0.59
     Contempor
    0.58
     Majefty
    0.58
     Anſ
    0.57
     lepro
    0.56
    Activations Density 0.171%

    No Known Activations