© 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. 20-CLT-HP
    7. 76985
    Prev
    Next
    INDEX
    Explanations

    technical/unusual texts

    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
    ReusableCell
    -0.45
     simples
    -0.35
    closePath
    -0.34
    лона
    -0.32
    Bibliografía
    -0.32
    Bibliografia
    -0.32
     linguagem
    -0.31
     Einfach
    -0.31
     Heft
    -0.30
    kologie
    -0.30
    POSITIVE LOGITS
    Perform
    0.69
     Perform
    0.69
     chóng
    0.67
     Efq
    0.66
    lapsingToolbar
    0.66
    Попис
    0.66
    ssysteme
    0.65
    ]--;
    0.65
    XmlAccessorType
    0.65
     perform
    0.64
    Activations Density 0.000%

    No Known Activations