© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30793
    Prev
    Next
    INDEX
    Explanations

    phrases related to hierarchical structures and dependencies in mathematics or logic

    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
    Negative Logits
    TagMode
    -0.81
    fiction
    -0.56
    Portály
    -0.56
     Opposite
    -0.54
     opposite
    -0.54
     Peak
    -0.51
    opposite
    -0.51
     Exactos
    -0.51
    ########.
    -0.51
    Opposite
    -0.50
    POSITIVE LOGITS
    يكب
    0.59
    SequentialGroup
    0.52
    StoreMessageInfo
    0.50
    berge
    0.49
     supérieures
    0.48
    Bioaccumulative
    0.48
    ::__
    0.47
    ⊃
    0.47
    حياته
    0.47
    mergeFrom
    0.47
    Activations Density 0.141%

    No Known Activations