© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 644
    Prev
    Next
    INDEX
    Explanations

    methods and processes related to manufacturing or invention, particularly focusing on composite materials and their applications

    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
     SafeMath
    -0.86
    hoeddwyd
    -0.82
    évaluateur
    -0.78
    ThroughAttribute
    -0.78
    AndEndTag
    -0.75
     resourceCulture
    -0.75
    oneofs
    -0.73
     BorderRadius
    -0.71
     désolés
    -0.71
    WriteTagHelper
    -0.69
    POSITIVE LOGITS
     Pe
    0.56
    </h5>
    0.50
    RuleContext
    0.45
    ex
    0.43
    Brun
    0.43
     Composition
    0.43
    AttributeSet
    0.43
    Interv
    0.43
     Brun
    0.43
     Pa
    0.43
    Activations Density 0.347%

    No Known Activations