© 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. 1035
    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
     for
    -0.66
    copg
    -0.58
     lift
    -0.50
    uglify
    -0.50
     untuk
    -0.49
     change
    -0.46
     increase
    -0.46
     pour
    -0.46
     redirect
    -0.46
     для
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.73
    matchCondition
    0.73
    windowFixed
    0.71
     EconPapers
    0.69
     StatefulWidget
    0.68
     "")
    0.65
    PerformLayout
    0.64
    MigrationBuilder
    0.60
    GroupLayout
    0.60
    ajari
    0.59
    Activations Density 0.011%

    No Known Activations