© 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. 4-CLT-HP
    7. 83
    Prev
    Next
    INDEX
    Explanations

    code

    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
    createCanvas
    -0.70
    oa̍t
    -0.68
     okuyayım
    -0.65
    }))
    -0.64
    DllImport
    -0.61
    )))));
    -0.61
    \{\\
    -0.61
    atedral
    -0.60
     चीज़ों
    -0.60
    ]))
    -0.60
    POSITIVE LOGITS
     ziren
    0.52
    مد
    0.48
     pratique
    0.47
     cheminée
    0.47
    έα
    0.47
     élève
    0.46
     oubli
    0.46
    湃
    0.45
     climatisation
    0.45
     néglig
    0.45
    Activations Density 0.038%

    No Known Activations