© 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. 786
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     solcher
    -0.47
     siitä
    -0.45
     undersigned
    -0.45
     које
    -0.45
    that
    -0.44
    mappedBy
    -0.44
     itself
    -0.43
     that
    -0.42
    them
    -0.42
     fato
    -0.42
    POSITIVE LOGITS
    EndInit
    0.82
     disambiguazione
    0.74
     ویکی‌پدی
    0.65
    DebuggerStep
    0.64
     kasarigan
    0.62
    httphttps
    0.61
     linkovi
    0.57
    最快更新
    0.54
    nitzer
    0.54
    expandindo
    0.53
    Activations Density 0.271%

    No Known Activations