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. 30437
    Prev
    Next
    INDEX
    Explanations

    sequences related to programming or coding structures

    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
    ])));
    -0.59
    "]));
    -0.59
    RetentionPolicy
    -0.57
    ########.
    -0.56
    Grandma
    -0.56
    Glej
    -0.55
    Kariera
    -0.54
    consulté
    -0.52
    Demografia
    -0.52
    edance
    -0.52
    POSITIVE LOGITS
    Datuak
    0.79
    IntoConstraints
    0.75
    ▪
    0.73
    parsedMessage
    0.66
     autorytatywna
    0.65
    +-+-
    0.63
    ForRow
    0.60
     Dä
    0.59
     StatefulWidget
    0.58
    XmlAccessType
    0.58
    Activations Density 0.007%

    No Known Activations