© 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. 1737
    Prev
    Next
    INDEX
    Explanations

    Parsed text snippets

    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
    uncia
    -0.45
     sınır
    -0.43
     menus
    -0.40
     localObject
    -0.40
    Números
    -0.40
    idać
    -0.39
     Archipelago
    -0.38
     setPassword
    -0.37
     shortlist
    -0.36
    offsetof
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.76
     utafitiHapana
    0.73
     ModelExpression
    0.72
     متعلقه
    0.71
    kloped
    0.70
    MethodManager
    0.70
    setVerticalGroup
    0.66
     CreateTagHelper
    0.65
    ItemLayout
    0.60
     NavController
    0.59
    Activations Density 0.004%

    No Known Activations