© 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. 92559
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    
    -0.82
     GenerationType
    -0.82
     "..\..\..\
    -0.73
     "..\..\
    -0.71
     للاسماء
    -0.69
    蚪
    -0.62
    oredCriteria
    -0.61
     الاطلاع
    -0.59
    zelf
    -0.59
    PreferredItem
    -0.59
    POSITIVE LOGITS
     Audiodateien
    0.56
     ioutil
    0.52
     szcze
    0.50
    Geografie
    0.46
    BeginContext
    0.45
    DataInputStream
    0.45
    ActionPerformed
    0.45
    insegna
    0.43
    Buffers
    0.41
     Wilber
    0.40
    Activations Density 0.069%

    No Known Activations