Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 1550
    Prev
    Next
    INDEX
    Explanations

    specialized terms related to food, its preparation, and production processes

    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
     ſche
    -0.91
     Monfieur
    -0.91
    ſelf
    -0.89
     becauſe
    -0.89
     Majefty
    -0.88
     purpoſe
    -0.87
     Jefus
    -0.86
     houſe
    -0.85
     reaſon
    -0.84
     Anſ
    -0.84
    POSITIVE LOGITS
    godic
    0.62
     FontFamily
    0.58
    bunda
    0.58
    complexContent
    0.57
    fini
    0.56
    醐
    0.55
    と呼ばれる
    0.54
     useAppContext
    0.54
    brtc
    0.54
    ingga
    0.53
    Activations Density 2.720%

    No Known Activations