© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    references to significant structural elements called "pillars," particularly highlighting their role as foundational or symbolic structures within a context

    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
     שוליים
    -0.71
    archiviato
    -0.69
    PyExc
    -0.66
     utafitiHapana
    -0.65
    XmlAccessType
    -0.63
     Meksiku
    -0.62
     "..\..\..\
    -0.59
    calaureate
    -0.59
    dersfield
    -0.59
     مرئيه
    -0.58
    POSITIVE LOGITS
     pillar
    3.89
    pillar
    3.69
     Pillar
    3.45
     pillars
    3.42
    pillars
    3.02
     Pillars
    2.91
     pilar
    2.80
     pilares
    2.38
     PILL
    1.75
    illar
    1.54
    Activations Density 0.001%

    No Known Activations