© 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. 12-RES-MATRYOSHKA-DC
    7. 28390
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical software and related terms

    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
     Waray
    -0.68
     فريبيس
    -0.66
    发表于
    -0.63
    BeginInit
    -0.62
     Roskov
    -0.62
    ########.
    -0.60
    ">—
    -0.59
     ویکی‌پدیا
    -0.57
     Gid
    -0.57
     AMR
    -0.57
    POSITIVE LOGITS
     SPSS
    1.51
     IBM
    0.67
     Footnote
    0.64
     RSSSF
    0.64
     Bein
    0.60
    intellij
    0.59
    chargez
    0.58
     religieuses
    0.58
     LIRE
    0.56
     Notes
    0.55
    Activations Density 0.002%

    No Known Activations