© 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. 1-CLT-HP
    7. 9178
    Prev
    Next
    INDEX
    Explanations

    wall

    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
     wall
    -0.73
    تقاوى
    -0.63
     Wall
    -0.61
    SourceChecksum
    -0.58
     walls
    -0.58
     kasarigan
    -0.58
    wall
    -0.56
    omores
    -0.53
     EconPapers
    -0.53
     Walls
    -0.52
    POSITIVE LOGITS
    routeProvider
    0.64
    RegistryLite
    0.63
     Wicidata
    0.61
    RetentionPolicy
    0.59
    MessageTagHelper
    0.57
    casila
    0.55
    bukkit
    0.54
    Itoa
    0.53
    StructEnd
    0.53
    bedo
    0.50
    Activations Density 0.054%

    No Known Activations