© 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. 30509
    Prev
    Next
    INDEX
    Explanations

    the action of simplifying mathematical expressions

    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
     pinulongan
    -0.93
     AssemblyProduct
    -0.86
    LookAnd
    -0.84
    ///</
    -0.80
     jLabel
    -0.78
    ($__
    -0.77
    ubri
    -0.77
    awtextra
    -0.76
     تضيفلها
    -0.75
     ProtoMessage
    -0.75
    POSITIVE LOGITS
    Simplify
    0.77
     ddelweddau
    0.63
     Simplify
    0.56
    Argumento
    0.54
    Denomin
    0.51
     compromised
    0.50
    TIMORE
    0.50
     antena
    0.47
     réduire
    0.46
    시오
    0.44
    Activations Density 0.009%

    No Known Activations