© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    mathematical notation indicating an infinite sequence or pattern

    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
    expandindo
    -1.02
    makeText
    -0.74
    
    -0.73
     مشين
    -0.69
    anyahu
    -0.69
    aarrggbb
    -0.67
    ilibrium
    -0.67
     Normdatei
    -0.66
    Билгалдахарш
    -0.66
     AssemblyCulture
    -0.66
    POSITIVE LOGITS
    ddots
    3.78
    ⋱
    1.23
    큼
    0.59
    vdots
    0.58
    subpackage
    0.55
    pherals
    0.52
    ENESS
    0.52
    IANT
    0.50
    WaitGroup
    0.50
     znam
    0.49
    Activations Density 0.000%

    No Known Activations