© 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. 1-CLT-HP
    7. 13605
    Prev
    Next
    INDEX
    Explanations

    legal/scientific documents

    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
    S
    -0.50
     
    -0.43
    En
    -0.43
    водов
    -0.42
    SUB
    -0.42
     en
    -0.41
    e
    -0.41
     En
    -0.41
     S
    -0.40
     le
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.97
    tagext
    0.96
     تضيفلها
    0.96
    OGND
    0.95
     gyhoeddwyd
    0.91
     للمعارف
    0.91
    曖昧さ回避
    0.91
     ویکی‌پدی
    0.90
    UnusedPrivate
    0.90
     дописавши
    0.89
    Activations Density 0.069%

    No Known Activations