© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 241
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    ंदीखरीदारी
    -0.82
    Personendaten
    -0.79
    interopRequire
    -0.79
    +#+#
    -0.78
    تقاوى
    -0.77
    новништво
    -0.75
    enumi
    -0.69
     ErrIntOverflow
    -0.67
    Искәрмәләр
    -0.65
     insuffisamment
    -0.65
    POSITIVE LOGITS
     a
    1.00
     an
    0.88
     eines
    0.64
     common
    0.60
     joint
    0.60
    一种
    0.58
     one
    0.57
     to
    0.57
     shared
    0.57
    an
    0.56
    Activations Density 0.008%

    No Known Activations