© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11338
    Prev
    Next
    INDEX
    Explanations

    genetic

    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
    :✨
    -0.93
    ItemBackground
    -0.84
     Roskov
    -0.82
    esez
    -0.82
    Geplaatst
    -0.79
     CreateTagHelper
    -0.79
    InjectAttribute
    -0.76
     AssemblyCulture
    -0.76
    WebVitals
    -0.75
     pinulongan
    -0.74
    POSITIVE LOGITS
     distance
    0.49
     distância
    0.47
     distances
    0.47
    distance
    0.46
     unité
    0.46
     cordes
    0.44
     Distance
    0.43
     distancia
    0.43
    IActionResult
    0.43
    Distance
    0.42
    Activations Density 0.040%

    No Known Activations