© 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. 11523
    Prev
    Next
    INDEX
    Explanations

    references to homologous genes or proteins

    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
    expandindo
    -0.89
     صوتيه
    -0.79
     InputDecoration
    -0.76
    AsUp
    -0.73
    "):
    -0.70
    %";
    -0.68
    theless
    -0.67
    tiness
    -0.66
    Портал
    -0.66
    IFICATE
    -0.66
    POSITIVE LOGITS
    ologous
    1.21
     homolog
    1.15
     homologous
    1.10
     homology
    0.97
    logous
    0.85
     Hom
    0.81
    Hom
    0.79
     Galbraith
    0.75
    homology
    0.73
     Moll
    0.71
    Activations Density 0.005%

    No Known Activations