© 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. 18-RES-MATRYOSHKA-DC
    7. 159
    Prev
    Next
    INDEX
    Explanations

    scientific references, specifically *Deinococcus radiodurans*

    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.18.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.18.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
    Panamoan
    -0.75
    pushFollow
    -0.72
    Життєпис
    -0.70
    السكان
    -0.68
    gunas
    -0.68
     betweenstory
    -0.67
    AddHtmlAttribute
    -0.67
    amerikanischer
    -0.67
     springfox
    -0.66
    PyExc
    -0.66
    POSITIVE LOGITS
    PhysRevD
    0.98
     DCP
    0.73
     Dör
    0.73
    AnchorStyles
    0.71
     DHS
    0.70
     DPR
    0.68
     DMR
    0.67
     DCA
    0.66
     Dres
    0.65
     DSS
    0.64
    Activations Density 3.094%

    No Known Activations