© 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. 2-RES-MATRYOSHKA-DC
    7. 3276
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical expressions and formal proof structures

    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
    setVerticalGroup
    -1.26
    SourceChecksum
    -1.09
    ViewFeatures
    -1.07
     للاسماء
    -0.97
    ])));
    -0.94
    WriteTagHelper
    -0.87
    Personensuche
    -0.85
     AppCompatTheme
    -0.85
    TagMode
    -0.85
    ).}
    -0.83
    POSITIVE LOGITS
     EconPapers
    0.49
    ↵↵
    0.44
    lana
    0.43
    мену
    0.41
     the
    0.41
    inu
    0.41
    ratto
    0.41
     sonst
    0.40
    žnost
    0.39
     чувство
    0.38
    Activations Density 7.293%

    No Known Activations