© 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. 28426
    Prev
    Next
    INDEX
    Explanations

    references to statistical significance or comparison in scientific research

    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
    DockStyle
    -1.07
    ViewFeatures
    -1.03
     ujednoznacz
    -1.03
     unknownFields
    -0.98
    elemField
    -0.98
    AndEndTag
    -0.96
     ProtoMessage
    -0.95
    setVerticalGroup
    -0.94
     typelib
    -0.93
     препратки
    -0.93
    POSITIVE LOGITS
    En
    0.44
    برة
    0.43
     En
    0.39
    ={`${
    0.39
     B
    0.38
     Procu
    0.37
     considera
    0.36
     [
    0.35
    pure
    0.35
    en
    0.35
    Activations Density 0.011%

    No Known Activations