© 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. 96465
    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
    ChildScrollView
    -0.53
    RenderAtEndOf
    -0.51
     therefore
    -0.51
     yourselves
    -0.50
    ósito
    -0.50
     LXX
    -0.49
    ตร์
    -0.49
    CodedInputStream
    -0.48
    therefore
    -0.47
    memoized
    -0.47
    POSITIVE LOGITS
    Hochspringen
    0.59
    #+#
    0.59
    Scénario
    0.57
     isolé
    0.56
    Weblinks
    0.52
    期刊论文
    0.52
    iecie
    0.52
     שוליים
    0.50
     Gonzalez
    0.50
    COUVER
    0.50
    Activations Density 0.003%

    No Known Activations