© 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. 98037
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    NameInMap
    -0.66
    ########.
    -0.50
     "..\..\..\
    -0.49
     Савезне
    -0.47
    gridy
    -0.45
    //
    -0.44
     Transfermarkt
    -0.43
    ittar
    -0.43
    टी
    -0.43
    venidos
    -0.43
    POSITIVE LOGITS
     InputDecoration
    0.64
     utafitiHapana
    0.59
    IsContent
    0.56
    migrationBuilder
    0.56
    ViewImports
    0.54
    "}")
    0.54
    TagMode
    0.53
     propOrder
    0.53
    DockStyle
    0.52
     defStyle
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.