© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2335
    Prev
    Next
    INDEX
    Explanations

    references to magic, witchcraft, and supernatural elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.99
    Personensuche
    -0.92
    principalColumn
    -0.87
    ErrorListener
    -0.86
     Rambo
    -0.85
    exitRule
    -0.78
    __(/*!
    -0.76
    fjspx
    -0.75
    GEBURTS
    -0.75
     שוליים
    -0.75
    POSITIVE LOGITS
     magic
    1.49
     Magic
    1.42
    magic
    1.34
    Magic
    1.32
     MAGIC
    1.32
     magia
    1.24
     magical
    1.21
    MAGIC
    1.18
     magique
    1.12
    magical
    1.11
    Activations Density 0.158%

    No Known Activations