© 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. 1699
    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
    ?
    -1.48
    .
    -1.07
    ,
    -0.98
    :
    -0.72
    !
    -0.70
    '
    -0.62
    "
    -0.61
    ...
    -0.59
    ?..
    -0.55
    )
    -0.53
    POSITIVE LOGITS
     fermés
    1.00
     cérami
    0.99
     automatiques
    0.99
     colorés
    0.98
     démocr
    0.94
     définiti
    0.93
     cœurs
    0.93
     découver
    0.92
     normaux
    0.91
     vectorielles
    0.90
    Activations Density 0.315%

    No Known Activations