© 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. 2-RES-MATRYOSHKA-DC
    7. 4727
    Prev
    Next
    INDEX
    Explanations

    references to the use or mention of magic, especially focusing on the word "magic" itself and related terms such as spells and sorcery

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndProject
    -0.71
    craper
    -0.62
    liothèque
    -0.59
    principalColumn
    -0.58
    ConstraintLayout
    -0.57
     Lamb
    -0.57
     Мексичка
    -0.56
     Rambo
    -0.55
     FileWriter
    -0.54
     TextStyle
    -0.53
    POSITIVE LOGITS
     magic
    3.45
     Magic
    3.22
    Magic
    3.19
    magic
    3.14
     MAGIC
    2.80
     magical
    2.64
    MAGIC
    2.50
     magia
    2.42
     magique
    2.42
    magical
    2.41
    Activations Density 0.109%

    No Known Activations