© 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. 398
    Prev
    Next
    INDEX
    Explanations

    when

    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
     you
    -0.59
     not
    -0.56
    Erreferentziak
    -0.56
     he
    -0.54
    存于互联网档案馆
    -0.51
    EndTag
    -0.49
     your
    -0.48
     least
    -0.48
    そんなに
    -0.47
    MockBean
    -0.47
    POSITIVE LOGITS
     newOwner
    0.58
     mathematician
    0.57
     برانيه
    0.55
    BeginContext
    0.55
    AddTagHelper
    0.54
     entrepreneur
    0.54
    wpi
    0.54
     ftate
    0.53
     AuthService
    0.52
    রা
    0.51
    Activations Density 0.003%

    No Known Activations