© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2624
    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
    tagHelperRunner
    -1.20
    ">//
    -1.09
     للمعارف
    -1.09
     autorytatywna
    -1.06
    SequentialGroup
    -1.00
     AssemblyCulture
    -0.94
     مشين
    -0.93
    +#+#
    -0.93
    jsxFileName
    -0.93
     protoimpl
    -0.92
    POSITIVE LOGITS
      
    0.60
    U
    0.50
    os
    0.49
     the
    0.46
     citoyens
    0.46
    F
    0.44
     or
    0.44
     it
    0.44
    W
    0.44
    ud
    0.44
    Activations Density 0.005%

    No Known Activations