© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71435
    Prev
    Next
    INDEX
    Explanations

    preposition by

    np_max-act-logits · 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
    Negative Logits
     EconPapers
    -0.98
     ſeveral
    -0.87
     Jefus
    -0.85
    RRect
    -0.85
     חיצוניים
    -0.83
     Efq
    -0.82
     theſe
    -0.82
    verwijspagina
    -0.81
    học
    -0.80
    parsedMessage
    -0.80
    POSITIVE LOGITS
    dant
    0.35
     is
    0.32
    ↵↵
    0.31
    ↵
    0.31
    rax
    0.29
    cting
    0.29
    tement
    0.29
    arna
    0.28
    izing
    0.28
     ak
    0.28
    Activations Density 0.009%

    No Known Activations