© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    capital letters that may be initials or part of acronyms

    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.18.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.18.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
     Winaray
    -0.92
    declarations
    -0.79
     AppColors
    -0.77
    ℉
    -0.63
    TagHelpers
    -0.61
     getItemCount
    -0.60
    nościo
    -0.60
     erkennt
    -0.59
     TextFormField
    -0.58
     Pech
    -0.57
    POSITIVE LOGITS
     bVar
    0.86
     nhiêu
    0.76
     nahilalakip
    0.74
     b
    0.73
     getB
    0.73
     bArr
    0.72
     BaseModel
    0.71
    ioutil
    0.71
     Basics
    0.70
    ButtonModule
    0.67
    Activations Density 2.230%

    No Known Activations