© 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. 20-CLT-HP
    7. 76233
    Prev
    Next
    INDEX
    Explanations

    technical and coded texts

    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
     initComponents
    -0.56
     kasarigan
    -0.53
     "..\..\
    -0.52
     &'
    -0.52
     RoutedEventArgs
    -0.49
    bufio
    -0.48
    uerre
    -0.48
    subpackage
    -0.47
    vább
    -0.47
     المعيارى
    -0.46
    POSITIVE LOGITS
    MENAFN
    0.68
    TestingModule
    0.64
    ftagPool
    0.59
    ̈́
    0.59
     high
    0.59
     hazardous
    0.58
     responsible
    0.58
    InjectAttribute
    0.57
    work
    0.56
     work
    0.56
    Activations Density 0.002%

    No Known Activations