© 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. 30317
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numerical 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
    estima
    -0.64
    lifford
    -0.59
     Imo
    -0.56
     Saks
    -0.53
    PostExecute
    -0.52
     putty
    -0.52
    Imo
    -0.52
    ATTR
    -0.51
     it
    -0.50
     Sak
    -0.50
    POSITIVE LOGITS
     IActionResult
    0.90
     Seel
    0.84
     Padova
    0.83
     propOrder
    0.81
     שוליים
    0.80
     Administrativna
    0.79
     StringTokenizer
    0.77
     ABO
    0.75
    "}")
    0.73
    webElement
    0.72
    Activations Density 0.275%

    No Known Activations