© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 6999
    Prev
    Next
    INDEX
    Explanations

    the presence of specific special characters and symbolic patterns within technical or mathematical notation

    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
     =",
    -0.96
    __":
    
    -0.89
     eventdata
    -0.86
     []:
    -0.85
     myſelf
    -0.84
    }();
    -0.83
     OnTriggerEnter
    -0.79
    TagHelper
    -0.78
     mues
    -0.77
     المعيارى
    -0.77
    POSITIVE LOGITS
    )=
    0.69
     coroa
    0.56
    庁
    0.56
    }=
    0.55
     l
    0.54
    })=
    0.54
     fiore
    0.54
    buc
    0.53
     Minerva
    0.52
     surpren
    0.52
    Activations Density 0.094%

    No Known Activations