© 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. 0-CLT-HP
    7. 95393
    Prev
    Next
    INDEX
    Explanations

    structures

    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
     structures
    -1.17
     Structures
    -1.13
    Structures
    -1.00
     STRUCTURES
    -0.97
    structures
    -0.95
     estructuras
    -0.79
    AlterField
    -0.78
    onAttach
    -0.76
     Strukturen
    -0.76
    rawDesc
    -0.74
    POSITIVE LOGITS
     kasarigan
    0.53
    cythe
    0.52
    стероид
    0.52
    InteropServices
    0.50
    isque
    0.50
     themselves
    0.48
     pinulongan
    0.48
     admitted
    0.46
    Warnings
    0.46
     वाला
    0.45
    Activations Density 0.049%

    No Known Activations