© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90690
    Prev
    Next
    INDEX
    Explanations

    subsidies

    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
    IUrlHelper
    -0.92
     للمعارف
    -0.91
    Personendaten
    -0.90
     subsidies
    -0.87
    SharedCtor
    -0.84
    PerformLayout
    -0.81
    yntaxException
    -0.79
    UPAC
    -0.78
     restrictions
    -0.77
    arounds
    -0.75
    POSITIVE LOGITS
    sk
    0.48
     willing
    0.42
    dze
    0.41
    sz
    0.40
     pó
    0.40
    ny
    0.39
    himself
    0.39
    ниці
    0.39
     }_{\
    0.38
     ठ
    0.38
    Activations Density 0.852%

    No Known Activations