© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3672
    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
    RegressionTest
    -0.56
    mpion
    -0.51
    밌
    -0.50
    iferous
    -0.49
    föl
    -0.49
     otomatig
    -0.49
    zepam
    -0.48
    parentId
    -0.48
    awtextra
    -0.47
    ISPR
    -0.47
    POSITIVE LOGITS
     الرياضيه
    0.65
     others
    0.59
     EconPapers
    0.58
    HomeAsUpEnabled
    0.55
    others
    0.55
    GEBURTSDATUM
    0.54
    dymyr
    0.54
     propOrder
    0.54
    nocache
    0.52
    FormTagHelper
    0.52
    Activations Density 0.004%

    No Known Activations