© 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. 5616
    Prev
    Next
    INDEX
    Explanations

    code snippets/internet data

    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
    \{\\
    -0.61
    modelBuilder
    -0.55
     KZ
    -0.50
    KeySpec
    -0.49
     MatDialog
    -0.48
     Def
    -0.45
     tumb
    -0.45
     للمعارف
    -0.44
     CreateTagHelper
    -0.43
     Crom
    -0.43
    POSITIVE LOGITS
     tiguan
    0.57
     cherchés
    0.57
     चीज़ों
    0.55
     credere
    0.52
     resourceCulture
    0.52
    RegressionTest
    0.50
     dAtA
    0.50
    ersham
    0.49
     vernac
    0.48
    WebElementEntity
    0.48
    Activations Density 0.005%

    No Known Activations