© 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. 0-CLT-HP
    7. 95100
    Prev
    Next
    INDEX
    Explanations

    scientific/math concepts

    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
     dignité
    -0.56
     complètes
    -0.48
    Obrázky
    -0.46
     attentes
    -0.46
     sekali
    -0.45
    ,
    -0.44
     kabel
    -0.44
     sanitarias
    -0.44
     mentales
    -0.43
     parete
    -0.43
    POSITIVE LOGITS
    ]='\
    0.84
     AssemblyCompany
    0.78
    IBarButtonItem
    0.78
    PreferredItem
    0.77
    +#+#
    0.77
    UnknownFields
    0.73
    AccessorTable
    0.71
    }$​
    0.70
    ]--;
    0.70
     ChromeDriver
    0.69
    Activations Density 0.011%

    No Known Activations