© 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. 3609
    Prev
    Next
    INDEX
    Explanations

    references to genetic elements and their significance in various contexts

    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
     tum
    -0.76
     Tum
    -0.73
    olum
    -0.67
    sider
    -0.66
    mble
    -0.65
    beke
    -0.63
     Ombudsman
    -0.63
     koh
    -0.63
     BER
    -0.62
     Mulligan
    -0.62
    POSITIVE LOGITS
    genetics
    1.10
     genetics
    1.05
    genetic
    1.03
     genetic
    0.98
     Genetic
    0.97
    Genetics
    0.94
    Genetic
    0.93
     Genetics
    0.93
     genética
    0.80
     genetically
    0.79
    Activations Density 0.009%

    No Known Activations