© 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. 22872
    Prev
    Next
    INDEX
    Explanations

    references to specific types of cancer, particularly glioblastoma and related terms

    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
     Adler
    -0.91
     FormControl
    -0.90
    PreAuthorize
    -0.88
     surla
    -0.80
     StringTokenizer
    -0.80
     vri
    -0.79
    цездатний
    -0.76
     Bergman
    -0.74
     '\\;'
    -0.74
    ImageContext
    -0.73
    POSITIVE LOGITS
     GB
    1.27
     Meg
    1.15
     meg
    1.14
     gb
    1.11
    Meg
    1.08
    GB
    1.06
     MEG
    0.95
     gigabyte
    0.93
    meg
    0.89
     Mega
    0.87
    Activations Density 0.022%

    No Known Activations