© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 989
    Prev
    Next
    INDEX
    Explanations

    Dashes and "The"

    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
    原始内容存档于
    -0.78
    MLLoader
    -0.71
     يتيمه
    -0.70
    istoitu
    -0.60
     BoxFit
    -0.59
    archiviato
    -0.57
    StoryboardSegue
    -0.56
    WriteTagHelper
    -0.55
    setVerticalGroup
    -0.54
    bkz
    -0.53
    POSITIVE LOGITS
     <=",
    0.62
     Members
    0.55
    Members
    0.51
     kasarigan
    0.50
    ญิง
    0.50
    Thousands
    0.47
     While
    0.47
    )}+\
    0.46
    The
    0.46
     With
    0.45
    Activations Density 0.009%

    No Known Activations