© 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. 0-CLT-HP
    7. 38573
    Prev
    Next
    INDEX
    Explanations

    effort or pressing forward

    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
    ed
    -0.79
     push
    -0.74
    e
    -0.74
    a
    -0.63
     pushed
    -0.62
     pushes
    -0.62
    ial
    -0.56
    pushed
    -0.55
    ing
    -0.53
    em
    -0.51
    POSITIVE LOGITS
    脚注の使い方
    0.86
     AssemblyCulture
    0.85
     فريبيس
    0.75
     Transfermarkt
    0.66
    TestingModule
    0.66
    AnimationsModule
    0.65
     AppColors
    0.63
    bootstrapcdn
    0.63
     gefragt
    0.61
    Zeneca
    0.61
    Activations Density 0.013%

    No Known Activations