© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 765
    Prev
    Next
    INDEX
    Explanations

    vocabulary that occurs in scientific writing related to cancer

    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
     McGu
    -0.59
     Rod
    -0.57
    ookie
    -0.56
    webElementXpaths
    -0.56
     Williamsburg
    -0.53
     StringVar
    -0.52
     estrés
    -0.52
     setObject
    -0.52
     Henson
    -0.52
     muñecas
    -0.50
    POSITIVE LOGITS
     tumor
    2.69
     Tumor
    2.55
     tumour
    2.45
     tumors
    2.34
    Tumor
    2.30
    tumor
    2.27
     Tumors
    2.19
     cancer
    2.16
     tumours
    2.09
     CANCER
    2.03
    Activations Density 0.307%

    No Known Activations