© 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. 5-CLT-HP
    7. 94832
    Prev
    Next
    INDEX
    Explanations

    performing actions

    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
     Meksiku
    -0.78
    Aholisi
    -0.60
    ineno
    -0.55
    клопе
    -0.53
     joaat
    -0.53
    types
    -0.53
    Soorten
    -0.52
     vVar
    -0.50
    LoadData
    -0.50
    : 
    -0.49
    POSITIVE LOGITS
     this
    0.65
     two
    0.52
    __(/*!
    0.51
    ropractic
    0.50
     թվական
    0.49
    Carriera
    0.49
    antry
    0.49
    PageFactory
    0.47
     three
    0.47
    beforeEach
    0.46
    Activations Density 0.038%

    No Known Activations