© 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. 5-CLT-HP
    7. 91832
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     Мексичка
    -0.91
    ⓧ
    -0.79
    Datuak
    -0.78
    UnusedPrivate
    -0.75
     الحره
    -0.74
    $}}
    -0.69
     '\\;'
    -0.68
    tagHelperRunner
    -0.68
    WebVitals
    -0.66
     pinulongan
    -0.66
    POSITIVE LOGITS
    ,
    0.61
    C
    0.56
    2
    0.54
    .
    0.51
     written
    0.51
    GTK
    0.50
     
    0.49
    JS
    0.49
    SVN
    0.48
    őle
    0.48
    Activations Density 0.019%

    No Known Activations