© 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. 4-CLT-HP
    7. 270
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     Expl
    -0.55
     magnify
    -0.50
    ogr
    -0.50
     tour
    -0.49
    gante
    -0.48
     quadrant
    -0.48
     notice
    -0.48
     Hildebrand
    -0.47
     Tufts
    -0.47
    qin
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.93
    CppMethod
    0.84
     estekak
    0.73
    SourceChecksum
    0.69
    )))),
    0.67
    IntoConstraints
    0.67
     بيها
    0.66
    ]")]
    0.65
     članak
    0.65
    LayoutStyle
    0.64
    Activations Density 0.041%

    No Known Activations