© 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. 5-CLT-HP
    7. 97173
    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
     Car
    -0.47
     CreateTagHelper
    -0.46
     Affaires
    -0.45
    hbase
    -0.44
    Legături
    -0.44
     HttpNotFound
    -0.44
     cra
    -0.43
    car
    -0.43
     car
    -0.43
    AndroidJUnit
    -0.43
    POSITIVE LOGITS
     >=",
    0.78
     purpoſe
    0.69
    ########.
    0.68
     iſt
    0.67
    RectangleBorder
    0.64
     चीज़ों
    0.63
     itſelf
    0.63
     ACE
    0.60
     ſtate
    0.59
     ſy
    0.59
    Activations Density 0.008%

    No Known Activations