© 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. 0-RES-MATRYOSHKA-DC
    7. 11015
    Prev
    Next
    INDEX
    Explanations

    references to religious hierarchy, authority figures, and related terminology

    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
    \{\\
    -0.77
    leyebilirsiniz
    -0.63
     cuánt
    -0.59
     useNavigate
    -0.59
     unmute
    -0.59
     RuntimeError
    -0.59
     "¿
    -0.58
    Notae
    -0.58
     препратки
    -0.58
    wpi
    -0.57
    POSITIVE LOGITS
    sizeCache
    0.59
     seperate
    0.55
    DebuggerStep
    0.54
     PRELIM
    0.51
     protoimpl
    0.50
    edig
    0.50
     undes
    0.50
    popper
    0.49
    ʁ
    0.49
    cev
    0.48
    Activations Density 0.053%

    No Known Activations