© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44086
    Prev
    Next
    INDEX
    Explanations

    ump

    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
     ump
    -0.98
     umpire
    -0.75
     Ump
    -0.68
    Ump
    -0.63
     kasarigan
    -0.60
    êques
    -0.57
    jstor
    -0.56
    MLLoader
    -0.55
    fitrión
    -0.54
    ViewStyle
    -0.54
    POSITIVE LOGITS
    teek
    0.56
    ]--;
    0.53
    ientôt
    0.52
    imte
    0.50
    teeth
    0.50
    ires
    0.49
    ธ์
    0.49
     trơn
    0.48
    امین
    0.48
    teen
    0.47
    Activations Density 0.327%

    No Known Activations