© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 175
    Prev
    Next
    INDEX
    Explanations

    chemicals ending in -osan/-ulan

    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
     المعيارى
    -0.42
    deld
    -0.40
    lab
    -0.39
    forRoot
    -0.37
    lob
    -0.37
    Trayectoria
    -0.37
     Stump
    -0.36
    deleteById
    -0.35
     ModelExpression
    -0.35
    mand
    -0.35
    POSITIVE LOGITS
    IsContent
    0.71
    nambuco
    0.68
     Efq
    0.68
    ⓧ
    0.67
    SerializedSize
    0.66
    PreferredItem
    0.66
     ویکی‌پدی
    0.64
    ніципалі
    0.63
     Theſe
    0.62
     olig
    0.62
    Activations Density 0.007%

    No Known Activations