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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8877
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or equations

    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
    ური
    -0.53
    TagMode
    -0.52
     durs
    -0.50
    calientes
    -0.49
     tribu
    -0.48
     Yen
    -0.47
     overwhel
    -0.46
    Dữ
    -0.46
    ckså
    -0.45
    Edm
    -0.45
    POSITIVE LOGITS
    Tikang
    0.70
    Personensuche
    0.67
     StatefulWidget
    0.65
    Diwedd
    0.63
    AndEndTag
    0.62
    readline
    0.56
     useStyles
    0.54
     /\.(
    0.54
    kháu
    0.54
     referrerpolicy
    0.52
    Activations Density 0.014%

    No Known Activations