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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38799
    Prev
    Next
    INDEX
    Explanations

    -tion noun endings

    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
    tions
    -0.93
     units
    -0.82
    tively
    -0.81
    ptions
    -0.79
    units
    -0.79
    исленность
    -0.77
    tionally
    -0.75
     pinulongan
    -0.74
    tion
    -0.71
     unités
    -0.69
    POSITIVE LOGITS
     Engines
    0.52
    ate
    0.47
     JpaRepository
    0.45
    ()`
    0.45
    KeySpec
    0.44
     ffilm
    0.43
     Aires
    0.43
     censiti
    0.43
    **/
    0.43
     deque
    0.43
    Activations Density 0.211%

    No Known Activations