© 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. 0-CLT-HP
    7. 43764
    Prev
    Next
    INDEX
    Explanations

    formal documents

    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
     one
    -0.72
     utafitiHapana
    -0.64
     unul
    -0.51
    cinia
    -0.51
     ones
    -0.51
    expandindo
    -0.50
     gainera
    -0.50
    #
    -0.50
    ivu
    -0.49
     ddelweddau
    -0.49
    POSITIVE LOGITS
    '}>
    0.56
     velkommen
    0.55
     UserRepository
    0.54
     ujednoznacz
    0.54
     balanceOf
    0.53
    beforeEach
    0.52
     drôle
    0.52
    setcounter
    0.51
    ::::::::
    0.50
    gages
    0.50
    Activations Density 0.029%

    No Known Activations