© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 2102
    Prev
    Next
    INDEX
    Explanations

    mentions of tumors and cancers, and related processes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     تضيفلها
    -1.05
    TagMode
    -0.89
     AssemblyCulture
    -0.85
    StoryboardSegue
    -0.78
    setVerticalGroup
    -0.77
    الإنجليزية
    -0.77
    SequentialGroup
    -0.76
    UnsafeEnabled
    -0.76
     AssemblyCompany
    -0.75
    InSection
    -0.73
    POSITIVE LOGITS
    igen
    0.80
     suppressor
    0.57
    VIAF
    0.56
    genicity
    0.51
    hyung
    0.46
    괴
    0.46
    igin
    0.46
    grow
    0.44
    Populations
    0.44
     Treating
    0.44
    Activations Density 0.027%

    No Known Activations