© 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. 1-RES-MATRYOSHKA-DC
    4. 414
    Prev
    Next
    INDEX
    Explanations

    patterns in parameterized mathematical expressions involving variables and functions

    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
    )}}
    -1.33
    ]))
    -1.20
    )))),
    -1.18
    })}
    -1.17
    )])
    -1.16
    }})
    -1.16
    )}
    -1.15
    ))}
    -1.11
    ))/
    -1.11
    ])]
    -1.10
    POSITIVE LOGITS
     AssemblyProduct
    0.67
    resizingMask
    0.57
    Initializable
    0.56
    CascadeType
    0.56
     TMPro
    0.55
     intptr
    0.54
     Kase
    0.53
     nakalista
    0.53
    <sub>
    0.52
    _{{\
    0.52
    Activations Density 14.867%

    No Known Activations