© 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. 20108
    Prev
    Next
    INDEX
    Explanations

    references to XOR or exclusive OR operations in the context of encryption or bit manipulation

    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
    Filmografie
    -0.66
    LOTTE
    -0.61
    깥
    -0.60
    hmigung
    -0.58
    tida
    -0.57
    醐
    -0.57
    alanta
    -0.57
    licula
    -0.56
    FLT
    -0.56
     Kershaw
    -0.56
    POSITIVE LOGITS
     XOR
    1.39
    XOR
    1.25
     xor
    0.94
     tartalomajánló
    0.87
     ^=
    0.85
     وتسجيلات
    0.82
    xor
    0.81
    NameInMap
    0.81
    Xor
    0.77
    addGap
    0.75
    Activations Density 0.001%

    No Known Activations