© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41041
    Prev
    Next
    INDEX
    Explanations

    end

    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
     end
    -1.05
     End
    -0.74
    End
    -0.73
    end
    -0.64
     endo
    -0.63
    tvguidetime
    -0.62
     END
    -0.60
    */),
    -0.60
     hydro
    -0.56
    🏻‍♀️
    -0.55
    POSITIVE LOGITS
     Protestants
    0.55
     kasarigan
    0.49
    idered
    0.48
    asjon
    0.47
    getDescriptor
    0.47
    ingly
    0.46
    τως
    0.44
    postolic
    0.44
     crucified
    0.44
     näky
    0.43
    Activations Density 0.017%

    No Known Activations