© 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. 4-CLT-HP
    7. 2144
    Prev
    Next
    INDEX
    Explanations

    just

    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
    Breath
    -0.50
    发表于
    -0.50
     bek
    -0.49
    Hozzáférés
    -0.49
     breath
    -0.48
    Personensuche
    -0.48
     Breath
    -0.47
     bathe
    -0.47
    entrion
    -0.47
     walk
    -0.47
    POSITIVE LOGITS
    CloseOperation
    0.74
    InjectAttribute
    0.70
     contextLoads
    0.62
    principalColumn
    0.58
    setVerticalGroup
    0.57
     '\\;'
    0.57
    ViewInit
    0.54
    $_['
    0.54
    zeczytaj
    0.52
    __).
    0.52
    Activations Density 0.003%

    No Known Activations