© 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. 5-CLT-HP
    7. 96509
    Prev
    Next
    INDEX
    Explanations

    the

    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
    featureID
    -0.68
    RectangleBorder
    -0.65
    "])
    -0.63
    原始内容存档于
    -0.61
    üyada
    -0.60
     Tất
    -0.59
    CDCl
    -0.59
     lenker
    -0.56
    󠁢
    -0.56
     تضيفلها
    -0.55
    POSITIVE LOGITS
    :✨
    0.50
     création
    0.47
    RetentionPolicy
    0.46
     malheur
    0.45
     only
    0.45
     généraux
    0.45
     fact
    0.45
     creation
    0.44
    zional
    0.44
     development
    0.44
    Activations Density 0.002%

    No Known Activations