© 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. 19975
    Prev
    Next
    INDEX
    Explanations

    references to specific dishes or cuisines

    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
    flashdata
    -0.49
    jface
    -0.47
    piri
    -0.46
    oler
    -0.45
    xase
    -0.45
    őle
    -0.45
    TemporalType
    -0.45
    请联系
    -0.45
    DAQ
    -0.44
     Bunt
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.92
    FormTagHelper
    0.72
    ztály
    0.70
     виправивши
    0.68
    seamnă
    0.61
     سكانية
    0.60
     للاسماء
    0.58
    upakan
    0.56
     nôtre
    0.56
    Diwedd
    0.55
    Activations Density 0.488%

    No Known Activations