© 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. 22-RES-MATRYOSHKA-DC
    7. 1181
    Prev
    Next
    INDEX
    Explanations

    language related to cancer treatment

    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
     مرئيه
    -0.91
    PerformLayout
    -0.72
     विश्वसनीयता
    -0.66
     Circulation
    -0.66
    Circ
    -0.65
     nakalista
    -0.63
    stateMutability
    -0.62
    AddTagHelper
    -0.61
    SourceChecksum
    -0.60
     Administrativna
    -0.60
    POSITIVE LOGITS
     radiation
    0.78
     irradiated
    0.75
     dose
    0.74
     irradiation
    0.73
     dosi
    0.68
     irradi
    0.65
     radiotherapy
    0.62
     Radiation
    0.61
    Dose
    0.61
    Radiation
    0.61
    Activations Density 0.446%

    No Known Activations