© 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. 4-CLT-HP
    7. 2695
    Prev
    Next
    INDEX
    Explanations

    century

    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
     actuelles
    -0.55
    $}}
    -0.53
    ofday
    -0.51
     ferons
    -0.51
     trouvait
    -0.50
    "}")
    -0.50
    })]
    -0.50
    ihnachts
    -0.50
     Estatal
    -0.48
    }))
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.55
     Turkey
    0.54
     Germany
    0.52
     Normdatei
    0.52
    достатки
    0.51
    GenerationType
    0.51
     America
    0.50
    র্ব
    0.50
     history
    0.49
    writeFieldEnd
    0.49
    Activations Density 0.006%

    No Known Activations