© 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. 20-CLT-HP
    7. 73539
    Prev
    Next
    INDEX
    Explanations

    transition to a state

    np_max-act-logits · 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
    TintMode
    -0.67
    endphp
    -0.66
    twimg
    -0.63
     scarce
    -0.61
     kasarigan
    -0.57
    脚注の使い方
    -0.54
    GraphicsUnit
    -0.52
     AspNetCore
    -0.52
    ніципалі
    -0.52
     EconPapers
    -0.51
    POSITIVE LOGITS
     became
    0.66
     dried
    0.65
     ran
    0.63
     Became
    0.62
     proved
    0.59
    Dry
    0.59
     Dry
    0.56
    DRY
    0.54
     dry
    0.54
    became
    0.54
    Activations Density 0.000%

    No Known Activations