© 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. 91596
    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
     bri
    -0.43
     Stahl
    -0.42
     eaters
    -0.42
    ULER
    -0.42
    webf
    -0.41
     Connie
    -0.41
     Rijks
    -0.41
    rmdir
    -0.40
    ulement
    -0.40
     Bri
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.86
     محفوظة
    0.85
    CloseOperation
    0.85
    GEBURTSDATUM
    0.77
     Réponses
    0.77
    تفصیلات
    0.76
    awtextra
    0.75
     الحره
    0.74
    قایناق‌لار
    0.70
     initComponents
    0.69
    Activations Density 0.010%

    No Known Activations