© 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. 22190
    Prev
    Next
    INDEX
    Explanations

    references to protein types and their designations

    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
    ChildScrollView
    -1.27
     Donat
    -1.01
    ]--;
    -0.91
     Leck
    -0.89
    ագրություններ
    -0.88
     Anſ
    -0.87
     ―――――
    -0.87
     protoimpl
    -0.84
    AndroidJUnit
    -0.82
     Reſ
    -0.82
    POSITIVE LOGITS
     PT
    1.31
    PT
    1.16
    pt
    1.12
     pt
    0.98
     pts
    0.83
    ProductType
    0.77
    Brady
    0.76
     Brady
    0.75
     tyme
    0.73
     perioada
    0.72
    Activations Density 0.036%

    No Known Activations