© 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. 4-CLT-HP
    7. 1093
    Prev
    Next
    INDEX
    Explanations

    parents

    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
    ArgsConstructor
    -0.57
    Története
    -0.57
    awaiter
    -0.56
     للمعارف
    -0.53
    crum
    -0.50
    alló
    -0.50
    windowFixed
    -0.50
    asana
    -0.47
     viewDidLoad
    -0.47
    -------
    -0.47
    POSITIVE LOGITS
     are
    0.73
     were
    0.72
    GEBURTSDATUM
    0.55
     اكتوبر
    0.55
    weren
    0.54
    izante
    0.54
     selves
    0.54
    FormTagHelper
    0.53
    Koordinaten
    0.53
     stedet
    0.53
    Activations Density 0.010%

    No Known Activations