© 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. 26075
    Prev
    Next
    INDEX
    Explanations

    arrays of numerical values related to structured data or commands in programming

    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
     оригіналу
    -1.02
    帖最后由
    -0.93
    AddTagHelper
    -0.82
     Normdatei
    -0.81
    +#+#
    -0.81
     препратки
    -0.79
    ViewFeatures
    -0.75
    AndEndTag
    -0.75
     typelib
    -0.75
     estekak
    -0.73
    POSITIVE LOGITS
     carried
    0.47
     Tapa
    0.44
    AZINE
    0.44
     Taz
    0.43
    trag
    0.43
     Efq
    0.43
    随
    0.40
    úgó
    0.40
    PART
    0.39
     devam
    0.38
    Activations Density 0.007%

    No Known Activations