© 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. 1-CLT-HP
    7. 10596
    Prev
    Next
    INDEX
    Explanations

    Heller

    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
    loss
    -0.64
    Bli
    -0.57
    citi
    -0.54
     Loss
    -0.54
     loss
    -0.52
     Heller
    -0.49
    zeb
    -0.48
     Force
    -0.47
    toma
    -0.47
    ('.'
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.73
    ResumeLayout
    0.69
    oredCriteria
    0.67
     وتسجيلات
    0.64
     extérieurs
    0.63
    ftagPool
    0.61
    expandindo
    0.60
    ReactDOM
    0.60
    figsize
    0.58
    انتهای
    0.57
    Activations Density 0.132%

    No Known Activations