© 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. 94382
    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
    <bos>
    -0.69
     Nguyen
    -0.49
     Its
    -0.46
    期刊论文
    -0.45
    tvguidetime
    -0.45
    setImageBitmap
    -0.45
     Culture
    -0.45
    instancetype
    -0.45
    SharedDtor
    -0.44
    ează
    -0.44
    POSITIVE LOGITS
     виправивши
    0.58
     ISNI
    0.55
     tenement
    0.52
     scolaires
    0.52
    IUrlHelper
    0.50
     tropics
    0.49
    ứa
    0.48
    ὸν
    0.48
     Nacionales
    0.48
     yetu
    0.47
    Activations Density 0.003%

    No Known Activations