© 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. 94292
    Prev
    Next
    INDEX
    Explanations

    Containing substring "feld"

    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
    feld
    -0.91
    zburg
    -0.60
    field
    -0.59
    brough
    -0.57
     field
    -0.50
    ovich
    -0.46
    Field
    -0.45
    jenih
    -0.43
    lovakia
    -0.43
    телна
    -0.42
    POSITIVE LOGITS
    AutoScale
    0.71
    XmlAccessorType
    0.71
     onCreateView
    0.70
    \{\\
    0.70
    principalColumn
    0.70
    TestingModule
    0.69
    تقاوى
    0.69
     Infórmanos
    0.68
     resourceCulture
    0.68
     estimés
    0.66
    Activations Density 1.185%

    No Known Activations