© 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. 28279
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating distance or extent

    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
    IUrlHelper
    -0.81
     يتيمه
    -0.80
    IndentedString
    -0.79
    例句
    -0.75
    ItemBackground
    -0.71
     Viitattu
    -0.67
    Trotz
    -0.67
     Walkover
    -0.67
     Warbler
    -0.66
     DataTypes
    -0.66
    POSITIVE LOGITS
     soweit
    0.53
    XmlRootElement
    0.52
     tanggung
    0.52
    monių
    0.52
     NDEBUG
    0.51
    вайтесь
    0.51
    RANGE
    0.49
     siihen
    0.49
     přev
    0.49
    uerst
    0.49
    Activations Density 0.004%

    No Known Activations