Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 42
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or formulas related to complex equations and 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
    ixante
    -0.79
    émon
    -0.78
    FORME
    -0.66
     Dol
    -0.65
     strto
    -0.63
     Requis
    -0.63
    Ế
    -0.62
    neth
    -0.61
    ÜR
    -0.60
    siez
    -0.60
    POSITIVE LOGITS
    ])
    2.33
    ))
    2.30
    )
    2.23
    })
    2.08
    ]))
    2.08
    ")
    2.05
    )])
    2.05
    ())
    2.03
    )
    2.03
    "))
    1.98
    Activations Density 3.470%

    No Known Activations