© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13852
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving matrix and tensor 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
    })));
    -0.67
    Duk
    -0.60
    ьаж
    -0.57
     Nehru
    -0.57
     Wap
    -0.57
    arson
    -0.57
    Fim
    -0.56
    Memento
    -0.55
    ríamos
    -0.54
    ttp
    -0.53
    POSITIVE LOGITS
    }[\
    1.98
     $[\
    1.20
    $[\
    0.83
    SpringBootTest
    0.71
    IntoConstraints
    0.71
     maternelle
    0.60
     CreateTagHelper
    0.60
     Sociales
    0.60
     tabac
    0.59
     Constitucional
    0.59
    Activations Density 0.001%

    No Known Activations