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. 72
    Prev
    Next
    INDEX
    Explanations

    numeric values or identifiers

    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
    ↵↵
    -0.73
    ↵
    -0.66
    .
    -0.54
    /
    -0.50
    You
    -0.49
     a
    -0.49
     "
    -0.49
    ("
    -0.49
    ,
    -0.48
     You
    -0.48
    POSITIVE LOGITS
    <bos>
    3.16
    ItemBackground
    1.34
     виправивши
    1.30
     Савезне
    1.28
     AspNetCore
    1.22
     disambiguazione
    1.21
    EndGlobalSection
    1.20
    WithIOException
    1.20
     мәкал
    1.16
    NUMX
    1.13
    Activations Density 0.004%

    No Known Activations