© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    mentions of types of cancer in the body

    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
     оригіналу
    -0.53
    ized
    -0.47
    defn
    -0.46
    ization
    -0.45
    devtool
    -0.44
    setof
    -0.43
    YSTEM
    -0.42
     MusicBrainz
    -0.41
     JUGA
    -0.41
    "]/
    -0.41
    POSITIVE LOGITS
     cancer
    0.96
    ContentAsync
    0.84
     Cancer
    0.78
     CANCER
    0.75
     carcinoma
    0.75
    contentLoaded
    0.74
    complexType
    0.73
    cancer
    0.71
     muualla
    0.64
    Cancer
    0.63
    Activations Density 0.025%

    No Known Activations