© 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. 5-CLT-HP
    7. 4235
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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
     تضيفلها
    -0.66
    kloped
    -0.60
    archiviato
    -0.55
     CreateTagHelper
    -0.53
     newsletters
    -0.51
    ValueStyle
    -0.51
     screening
    -0.50
    ьаж
    -0.50
     feeds
    -0.50
    реб
    -0.49
    POSITIVE LOGITS
    Зноскі
    0.52
    Expedia
    0.51
    ActionCreators
    0.51
    发表于
    0.50
    photobucket
    0.48
     wireType
    0.48
     flé
    0.48
     picha
    0.47
     Plung
    0.47
    ATTER
    0.47
    Activations Density 0.002%

    No Known Activations