© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4937
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vér
    -0.42
     réactions
    -0.42
     Individ
    -0.41
     Europy
    -0.40
     choc
    -0.39
     Scro
    -0.39
    NVIC
    -0.39
     reak
    -0.38
    trato
    -0.38
     beh
    -0.38
    POSITIVE LOGITS
    ImageContext
    0.90
     lenker
    0.89
     שוליים
    0.86
     disambiguazione
    0.86
    migrationBuilder
    0.85
    曖昧さ回避
    0.79
    \{\\
    0.78
    complexContent
    0.78
    ]--;
    0.77
    
    0.77
    Activations Density 0.224%

    No Known Activations