© 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. 666
    Prev
    Next
    INDEX
    Explanations

    identifiers (often codes related to interfaces or standards) that contain GT, LT, PT, MD or IFT

    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
    ільки
    -0.76
    diğimiz
    -0.70
    Życiorys
    -0.67
    ніципалі
    -0.66
    houden
    -0.65
    ed
    -0.64
     CreateTagHelper
    -0.64
     cref
    -0.63
    holder
    -0.63
    ize
    -0.61
    POSITIVE LOGITS
    ت
    0.72
    ting
    0.71
    tttt
    0.70
     Trit
    0.70
    ttt
    0.69
    tott
    0.65
    ft
    0.60
    t
    0.59
     Weit
    0.59
    at
    0.59
    Activations Density 1.109%

    No Known Activations