© 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. 3160
    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
    Hochspringen
    -0.55
    DJANGO
    -0.51
     ModelExpression
    -0.50
    inerea
    -0.50
    saraba
    -0.48
     trabajando
    -0.47
     发表于
    -0.47
     Maß
    -0.47
    indari
    -0.47
    ChildIndex
    -0.46
    POSITIVE LOGITS
     ExecuteAsync
    0.55
    ритори
    0.49
    ItemBackground
    0.49
    gameserver
    0.48
    MessageInfo
    0.48
    homonymie
    0.48
    ethers
    0.48
     صوتيه
    0.47
    hip
    0.47
    ufort
    0.47
    Activations Density 0.003%

    No Known Activations