© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4682
    Prev
    Next
    INDEX
    Explanations

    XML/Android code

    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
     للمعارف
    -0.81
    OrNil
    -0.60
    ViewFeatures
    -0.56
    ContentLoaded
    -0.56
    Gön
    -0.56
    ❉
    -0.55
    itent
    -0.52
     AssemblyTitle
    -0.52
    AddTagHelper
    -0.52
    úng
    -0.52
    POSITIVE LOGITS
    ulating
    0.51
    ulation
    0.47
    laf
    0.47
    ulas
    0.44
    Queryable
    0.44
    PageFactory
    0.43
     flujo
    0.42
    OSHA
    0.42
     EClass
    0.42
    ulkner
    0.41
    Activations Density 0.003%

    No Known Activations