© 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. 446
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific studies and lab analysis.

    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
    RegistryLite
    -0.64
    JoinColumn
    -0.62
    Externé
    -0.60
    ceptre
    -0.59
    JoinTable
    -0.58
     trasparente
    -0.58
    antee
    -0.58
    GeneratedCode
    -0.57
    webElementXpaths
    -0.56
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     analysis
    0.86
     analyses
    0.73
    analysis
    0.69
     analisis
    0.67
     análisis
    0.65
     Analysis
    0.65
     tests
    0.64
    ImageContext
    0.63
     assays
    0.63
     microscopy
    0.63
    Activations Density 2.719%

    No Known Activations