© 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. 72706
    Prev
    Next
    INDEX
    Explanations

    Code and programming jargon

    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
     ویکی‌پدیا
    -0.56
     referenties
    -0.56
    setImageBitmap
    -0.51
    ecap
    -0.49
    RTLR
    -0.47
    ssen
    -0.47
     sais
    -0.47
     foot
    -0.47
     Lu
    -0.46
    oons
    -0.46
    POSITIVE LOGITS
     ComVisible
    0.63
     يتيمه
    0.60
    tanleria
    0.58
    SourceChecksum
    0.57
     aapt
    0.56
     initComponents
    0.55
     disambiguazione
    0.55
     transférez
    0.54
    IntoConstraints
    0.54
    HasAnnotation
    0.54
    Activations Density 0.000%

    No Known Activations