© 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. 72878
    Prev
    Next
    INDEX
    Explanations

    struct

    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
     disambiguazione
    -0.99
     cherchés
    -0.83
     ostavi
    -0.76
    WithIOException
    -0.75
     magasiner
    -0.74
    脚注の使い方
    -0.74
    AsUp
    -0.73
     '\\;'
    -0.73
     Infórmanos
    -0.70
     intptr
    -0.69
    POSITIVE LOGITS
    CodeAttribute
    0.49
    TableCell
    0.46
    ura
    0.45
    ograd
    0.42
     Tur
    0.40
    Tur
    0.38
     take
    0.37
     plastic
    0.37
    AxisAlignment
    0.36
    mitten
    0.36
    Activations Density 0.000%

    No Known Activations