© 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. 29752
    Prev
    Next
    INDEX
    Explanations

    lines or sections with numerical data and structured formats

    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
     Jehová
    -0.54
     Añade
    -0.50
     rimu
    -0.48
    جهزة
    -0.46
     elsewhere
    -0.46
    плек
    -0.45
     responsabilità
    -0.45
    SharedDtor
    -0.44
     indir
    -0.43
     reje
    -0.43
    POSITIVE LOGITS
     дописавши
    0.81
     Мексичка
    0.81
    Datuak
    0.76
    AddTagHelper
    0.73
    NewUrlParser
    0.73
    :✨
    0.73
    NamedQueries
    0.71
    EndGlobalSection
    0.70
     >=",
    0.69
    SourceChecksum
    0.69
    Activations Density 0.012%

    No Known Activations