© 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. 5-CLT-HP
    7. 467
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    RegressionTest
    -0.58
    ↵↵
    -0.52
    appearance
    -0.47
    locate
    -0.45
    )}>
    -0.45
     Sech
    -0.44
     họp
    -0.44
    ProcessEvent
    -0.44
    </table>
    -0.43
    use
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.72
    NameInMap
    0.70
     '\\;'
    0.65
    Geplaatst
    0.64
    verwijspagina
    0.62
     femininas
    0.62
    elfde
    0.59
    endpush
    0.59
    AutoresizingMask
    0.58
     ujednoznacz
    0.57
    Activations Density 0.011%

    No Known Activations