© 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. 30071
    Prev
    Next
    INDEX
    Explanations

    terms associated with cancerous conditions, specifically malignancy

    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
     AssemblyCulture
    -1.16
     CreateTagHelper
    -1.13
    tagHelperRunner
    -0.98
    LookAnd
    -0.93
     ujednoznacz
    -0.93
     المعيارى
    -0.91
     дописавши
    -0.90
    Portail
    -0.89
     propOrder
    -0.88
     فريبيس
    -0.88
    POSITIVE LOGITS
     malignant
    0.93
    ignant
    0.91
     Mal
    0.74
     MAL
    0.69
     Mald
    0.60
    IFEST
    0.60
    uskas
    0.56
    nski
    0.55
    Mal
    0.55
    mali
    0.54
    Activations Density 0.003%

    No Known Activations