© 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. 20-CLT-HP
    7. 77247
    Prev
    Next
    INDEX
    Explanations

    programming/technical content

    np_max-act-logits · 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
     estekak
    -0.61
     공식
    -0.49
    adaptiveStyles
    -0.48
    PerformLayout
    -0.48
    toCharArray
    -0.47
    Controllo
    -0.47
    Datuak
    -0.47
    cyklopedia
    -0.47
    BeginContext
    -0.46
    %;
    -0.45
    POSITIVE LOGITS
    FileChooser
    0.68
     betweenstory
    0.59
     spared
    0.56
    tableFuture
    0.55
    urlpatterns
    0.55
     NSCoder
    0.53
    SOCK
    0.53
    SpringRunner
    0.52
     ArrayAdapter
    0.52
     kaarangay
    0.51
    Activations Density 0.001%

    No Known Activations