© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97560
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings

    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
    StandardCharsets
    -0.47
    ernos
    -0.47
    期刊论文
    -0.46
    InteropServices
    -0.45
    ExecuteReader
    -0.43
    ((&
    -0.42
    wo
    -0.41
    셨
    -0.40
     đáo
    -0.40
    bitset
    -0.40
    POSITIVE LOGITS
    DockStyle
    0.77
    ChildScrollView
    0.77
     abstrait
    0.74
     للمعارف
    0.73
    الحياه
    0.71
     fallu
    0.68
     Boring
    0.65
    afficheront
    0.61
     fumée
    0.60
     payé
    0.60
    Activations Density 0.065%

    No Known Activations