© 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. 2060
    Prev
    Next
    INDEX
    Explanations

    that

    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
     repre
    -0.46
    //});
    -0.43
     ब्रेकडाउन
    -0.41
     des
    -0.40
    "}")
    -0.40
     routinely
    -0.40
    อื่น
    -0.40
    架
    -0.40
     useContext
    -0.40
    (',');
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     typelib
    0.80
    Portail
    0.74
    ^(@)
    0.74
    Autoritní
    0.73
    ContentAsync
    0.73
     lenker
    0.73
    HideFlags
    0.71
    PerformLayout
    0.71
    -------------</
    0.71
    Activations Density 0.002%

    No Known Activations