© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 722
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical distributions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     canadienne
    -0.74
     canadien
    -0.74
    nbt
    -0.69
     Beaufort
    -0.69
     Leroy
    -0.68
    Pty
    -0.67
    Durata
    -0.66
     oocytes
    -0.66
     Egl
    -0.66
    XHR
    -0.65
    POSITIVE LOGITS
     distribution
    1.63
     distribu
    1.50
     Distribution
    1.47
     distributions
    1.47
     distributing
    1.46
    distribution
    1.39
    Distribution
    1.38
     distribute
    1.37
     Distributions
    1.37
     distributes
    1.34
    Activations Density 0.152%

    No Known Activations