© 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. 11774
    Prev
    Next
    INDEX
    Explanations

    references to the act of moving or transferring

    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
    CloseOperation
    -0.79
    +#+
    -0.63
    ScopeManager
    -0.62
    ="@+
    -0.60
    enfone
    -0.58
     beij
    -0.57
    PagerAdapter
    -0.55
    CppMethod
    -0.54
     breathed
    -0.53
     Forderungen
    -0.53
    POSITIVE LOGITS
     relocation
    2.81
     relocated
    2.80
     relocate
    2.80
     Relocation
    2.47
     relocating
    2.45
     kasarigan
    0.79
     displaced
    0.77
     resettlement
    0.75
    Rel
    0.71
     translocation
    0.71
    Activations Density 0.000%

    No Known Activations