© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43221
    Prev
    Next
    INDEX
    Explanations

    function

    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
     function
    -1.73
    function
    -1.51
     Function
    -1.06
     función
    -1.00
     fungsi
    -0.91
    Function
    -0.90
     Funktion
    -0.90
     fonction
    -0.90
     funzione
    -0.88
     функция
    -0.87
    POSITIVE LOGITS
    ization
    0.91
    ized
    0.77
    ality
    0.72
    izing
    0.70
    izations
    0.66
    ally
    0.60
    ised
    0.60
    ize
    0.60
     CURIAM
    0.60
    ary
    0.59
    Activations Density 0.086%

    No Known Activations