© 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. 20311
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to quantum fields and transformations

    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
    ToBounds
    -0.57
    رشف
    -0.55
    pyx
    -0.51
     absl
    -0.47
     Juf
    -0.47
     handleMessage
    -0.47
     withal
    -0.46
     sceptre
    -0.45
    hending
    -0.45
     thyself
    -0.44
    POSITIVE LOGITS
    enumi
    0.65
    tagHelperRunner
    0.65
    enterOuterAlt
    0.63
    enumii
    0.59
    RegressionTest
    0.59
     الرياضيه
    0.58
    fjspx
    0.56
    jsii
    0.53
    󠁢
    0.53
    exitRule
    0.52
    Activations Density 0.047%

    No Known Activations