© 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. 637
    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
    
    -0.72
     ExecuteAsync
    -0.70
    awtextra
    -0.69
    lyon
    -0.64
    sizeCache
    -0.63
    ModelSerializer
    -0.63
     deleteById
    -0.62
     ModelRenderer
    -0.62
     Need
    -0.59
     esternos
    -0.59
    POSITIVE LOGITS
     build
    0.54
     advance
    0.54
     foster
    0.51
     mold
    0.50
     drive
    0.50
     help
    0.50
     pave
    0.48
     mould
    0.47
     steer
    0.47
     spread
    0.45
    Activations Density 0.005%

    No Known Activations