© 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. 0-RES-MATRYOSHKA-DC
    7. 12982
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "magic" or "magical" properties

    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
     magical
    -0.80
    magical
    -0.68
     mystical
    -0.60
     Industrial
    -0.58
     magically
    -0.56
     miraculously
    -0.56
     FileWriter
    -0.56
     SWIG
    -0.55
    Industrial
    -0.53
     textStatus
    -0.52
    POSITIVE LOGITS
     Magic
    2.06
    Magic
    1.67
    MAGIC
    1.17
     MAGIC
    1.13
    OGND
    0.62
    blic
    0.59
    oltre
    0.58
     سكانية
    0.58
    出版年
    0.57
    マジック
    0.56
    Activations Density 0.001%

    No Known Activations