© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46058
    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
     crucial
    -0.71
     critical
    -0.64
     of
    -0.59
     and
    -0.59
     key
    -0.54
     or
    -0.52
     -
    -0.51
     +
    -0.51
    ,
    -0.50
     vital
    -0.49
    POSITIVE LOGITS
     Efq
    1.07
     greateſt
    0.98
     themſelves
    0.98
     myſelf
    0.97
     purpoſe
    0.97
     whoſe
    0.95
     itſelf
    0.95
    ſelves
    0.95
     uſed
    0.93
     Theſe
    0.92
    Activations Density 0.010%

    No Known Activations