© 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. 1717
    Prev
    Next
    INDEX
    Explanations

    references to spatial positions, particularly related to the top and bottom layouts of items or layers

    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
    loroethene
    -0.65
    flug
    -0.63
    adeloupe
    -0.63
     Réponses
    -0.62
     AssemblyCompany
    -0.61
    */),
    -0.61
    Ẽ
    -0.61
    erobic
    -0.60
     canali
    -0.60
    huawei
    -0.60
    POSITIVE LOGITS
     TOP
    1.83
    TOP
    1.70
     Top
    1.57
     top
    1.55
     tops
    1.52
    top
    1.51
    Top
    1.49
     Tops
    1.47
    getTop
    1.38
    tops
    1.28
    Activations Density 0.169%

    No Known Activations