© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5732
    Prev
    Next
    INDEX
    Explanations

    importance placed on commas in sentence construction

    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
    .
    -0.58
    RectangleBorder
    -0.50
     quibus
    -0.47
    The
    -0.45
     }^{[
    -0.44
    U
    -0.43
    ConfigureAwait
    -0.42
    ↵↵
    -0.42
    Since
    -0.42
    There
    -0.41
    POSITIVE LOGITS
    ratulations
    1.06
    ^(@)
    0.93
    Collegamenti
    0.85
    */;
    0.82
     autorytatywna
    0.81
    terday
    0.77
    NUMX
    0.77
    heast
    0.76
    ruary
    0.76
    ressee
    0.76
    Activations Density 0.408%

    No Known Activations