© 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. 238
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to materials science, engineering, and scientific research, particularly focusing on composite materials, hydrogels, and their applications in tissue engineering and energy-related fields.

    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
    AndEndTag
    -0.67
    PLANATION
    -0.56
     confirmer
    -0.54
    setColumns
    -0.52
    assumed
    -0.50
    AddColumn
    -0.50
    bijt
    -0.49
    uerst
    -0.49
     darf
    -0.48
     assumed
    -0.47
    POSITIVE LOGITS
     novel
    0.90
     nano
    0.84
     nan
    0.83
     nanos
    0.80
     miniatur
    0.79
     scalable
    0.79
     innovative
    0.77
    LookAnd
    0.77
     versatile
    0.76
     engineered
    0.76
    Activations Density 4.125%

    No Known Activations