© 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. 97806
    Prev
    Next
    INDEX
    Explanations

    prepositions and location words

    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
    ingtones
    -0.45
     informant
    -0.43
    AuthProvider
    -0.42
    oa̍t
    -0.42
    Karakteristik
    -0.41
    GMENT
    -0.41
    xically
    -0.41
    PackageManager
    -0.40
    зможно
    -0.40
     MOSFET
    -0.40
    POSITIVE LOGITS
     يتيمه
    0.68
     autorytatywna
    0.68
    setupUi
    0.63
    DockStyle
    0.62
    principalTable
    0.61
    migrationBuilder
    0.60
     }{@
    0.60
     متعلقه
    0.60
    interopRequire
    0.59
    Архівовано
    0.59
    Activations Density 0.001%

    No Known Activations