© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    discussions about historical context and implications of slavery, particularly focusing on the contributions and significance of enslaved people

    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
     {}));
    -0.80
    
    -0.72
     @}
    -0.61
     урна
    -0.59
     Савезне
    -0.56
    ieteur
    -0.54
    orphic
    -0.54
    󠁢
    -0.54
    styleType
    -0.53
    atario
    -0.52
    POSITIVE LOGITS
     dependence
    0.69
    dependence
    0.67
     indispensable
    0.66
    dependency
    0.66
     vitale
    0.65
     dependency
    0.64
     Dependence
    0.63
     indispens
    0.63
     essential
    0.62
    essential
    0.61
    Activations Density 0.120%

    No Known Activations