© 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. 4-CLT-HP
    7. 1641
    Prev
    Next
    INDEX
    Explanations

    onic

    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
     volume
    -0.39
    kháu
    -0.39
     formed
    -0.38
    Демографія
    -0.38
     order
    -0.36
    createServer
    -0.36
     correctes
    -0.36
     financed
    -0.36
     offered
    -0.35
    kuti
    -0.35
    POSITIVE LOGITS
    ⓧ
    0.77
     Normdatei
    0.74
    protoimpl
    0.72
     &___
    0.70
    onAttach
    0.68
    MethodManager
    0.67
    
    0.65
     propOrder
    0.62
     pinulongan
    0.61
    aarrggbb
    0.61
    Activations Density 0.003%

    No Known Activations