© 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. 999
    Prev
    Next
    INDEX
    Explanations

    sections of product descriptions and manuals.

    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
     متعلقه
    -0.68
     NSCoder
    -0.62
    LookAnd
    -0.61
    openzeppelin
    -0.60
    ArgsConstructor
    -0.54
     pulumi
    -0.52
    '][]
    -0.50
    LTE
    -0.50
     Arquite
    -0.49
    unnitel
    -0.47
    POSITIVE LOGITS
     cleaning
    2.25
     clean
    2.11
     cleans
    1.99
     Cleaning
    1.98
     Clean
    1.98
     cleaned
    1.96
    Clean
    1.91
    clean
    1.88
    Cleaning
    1.87
    cleaning
    1.83
    Activations Density 1.201%

    No Known Activations