© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    password

    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
     taşı
    -0.47
    脚注の使い方
    -0.46
     contributions
    -0.45
    hql
    -0.44
     logs
    -0.44
    voli
    -0.44
     program
    -0.43
     contribution
    -0.43
    cra
    -0.43
     osobow
    -0.43
    POSITIVE LOGITS
    antMatchers
    0.59
    帖最后由
    0.59
    GEBURTSDATUM
    0.58
     NDEBUG
    0.58
    invokeLater
    0.56
    uevas
    0.55
     abstrato
    0.52
    ffield
    0.52
    Blick
    0.52
    )]);
    0.51
    Activations Density 0.011%

    No Known Activations