© 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. 923
    Prev
    Next
    INDEX
    Explanations

    references to research article identifiers

    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
     autorytatywna
    -0.94
    MigrationBuilder
    -0.83
     tartalomajánló
    -0.82
    FormTagHelper
    -0.81
    SharedDtor
    -0.80
    msgTypes
    -0.79
    plotlib
    -0.78
    ptonshire
    -0.73
    DockStyle
    -0.72
     ویکی‌آمباردا
    -0.71
    POSITIVE LOGITS
     PLoS
    0.62
    PONE
    0.60
    pone
    0.56
    ************/
    0.53
    )))),
    0.45
     PLOS
    0.44
     genome
    0.44
     ""));
    0.43
    ********/
    0.42
     khoa
    0.41
    Activations Density 0.252%

    No Known Activations