© 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. 981
    Prev
    Next
    INDEX
    Explanations

    percentages and related words.

    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
    ниципа
    -0.70
    IContainer
    -0.69
    TagHelper
    -0.66
    IUrlHelper
    -0.66
    yntaxException
    -0.66
     betweenstory
    -0.60
    GraphicsUnit
    -0.60
     שוליים
    -0.59
     ErrIntOverflow
    -0.59
    DockStyle
    -0.58
    POSITIVE LOGITS
     majority
    0.81
     nearly
    0.81
     almost
    0.79
     ninety
    0.77
     (%)
    0.77
     Nearly
    0.73
     Almost
    0.73
    Nearly
    0.72
     eighty
    0.72
    Almost
    0.69
    Activations Density 0.700%

    No Known Activations