© 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. 4-CLT-HP
    7. 1050
    Prev
    Next
    INDEX
    Explanations

    electrical outlets/sockets

    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
    BagLayout
    -0.56
     CGSize
    -0.56
    quehanna
    -0.48
    lorus
    -0.47
    =""></
    -0.46
    nonatomic
    -0.46
     Magdeburg
    -0.45
    isia
    -0.45
     Buchen
    -0.45
    Person
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.68
    featureID
    0.66
     kasarigan
    0.65
    MigrationBuilder
    0.62
    rrggbb
    0.60
    ThroughAttribute
    0.59
     calendriers
    0.57
    sunter
    0.57
     AssemblyCulture
    0.53
    Дереккөздер
    0.53
    Activations Density 0.001%

    No Known Activations