© 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. 6-RES-MATRYOSHKA-DC
    7. 947
    Prev
    Next
    INDEX
    Explanations

    technical language from scientific papers, particularly related to cancer and cellular 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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubel
    -0.55
    SourceChecksum
    -0.48
     con
    -0.48
     him
    -0.46
    置き
    -0.42
    RTLD
    -0.42
     natural
    -0.41
    ™
    -0.41
     im
    -0.40
     כן
    -0.40
    POSITIVE LOGITS
    InvalidProtocol
    0.73
    makeText
    0.68
    enterOuterAlt
    0.68
    ⤹
    0.68
    AndroidJUnit
    0.67
     näin
    0.67
     Pingback
    0.66
     useRouter
    0.65
    IsPostBack
    0.65
     <<<<<<<<<<<<<<
    0.64
    Activations Density 2.044%

    No Known Activations