© 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. 94555
    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
    DockStyle
    -0.52
    }{||
    -0.50
     função
    -0.44
     mal
    -0.44
    os
    -0.43
     useState
    -0.42
    ISupport
    -0.42
     possuem
    -0.41
     createState
    -0.41
     aimez
    -0.41
    POSITIVE LOGITS
     myſelf
    0.75
     cherchés
    0.66
    oa̍t
    0.63
     doubtnut
    0.62
     Monfieur
    0.59
     tanong
    0.59
     дописавши
    0.58
     reaſon
    0.58
     perfons
    0.58
     kaarangay
    0.57
    Activations Density 0.001%

    No Known Activations