© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17843
    Prev
    Next
    INDEX
    Explanations

    terms related to defining and differentiating types of figures or objects, especially in a technical or product description context

    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
    featureID
    -0.81
    出版年
    -0.73
    
    -0.73
    PerformLayout
    -0.69
    AsUp
    -0.68
     '{@
    -0.66
     InputDecoration
    -0.65
    </thead>
    -0.64
     Мексичка
    -0.62
     ©️
    -0.60
    POSITIVE LOGITS
     or
    0.62
     või
    0.58
     Alternatively
    0.57
     아니라
    0.53
    mobileqq
    0.52
    或
    0.51
    Alternatively
    0.50
     либо
    0.49
    或者
    0.49
     Trabalho
    0.49
    Activations Density 0.737%

    No Known Activations