© 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. 31905
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical expressions and symbols

    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
     intptr
    -0.63
     ovale
    -0.53
    x
    -0.48
     şeyi
    -0.47
     layak
    -0.47
     arma
    -0.45
    Salta
    -0.44
     magasiner
    -0.43
    ServletConfig
    -0.43
    Vanjske
    -0.41
    POSITIVE LOGITS
    ImageContext
    0.82
    脚注の使い方
    0.73
    原始内容存档于
    0.71
    oneofs
    0.69
    IsContent
    0.69
    cinated
    0.69
    īdz
    0.68
    resave
    0.66
     dead
    0.64
    Dead
    0.64
    Activations Density 0.036%

    No Known Activations