© 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. 304
    Prev
    Next
    INDEX
    Explanations

    structured data attributes related to programming or coding contexts

    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
    IVEREF
    -0.66
     NSCoder
    -0.61
    ThemeOverlay
    -0.57
     câte
    -0.56
     leden
    -0.55
     giudizio
    -0.55
     estratégico
    -0.54
    forChild
    -0.54
    #+#
    -0.53
    Demografie
    -0.53
    POSITIVE LOGITS
    $_.
    0.68
    VIAF
    0.65
    """.
    0.65
    jstor
    0.65
     CURLOPT
    0.65
    "]();
    0.60
    DataAnnotations
    0.59
    ')['
    0.57
     Wicidata
    0.56
    ',{
    0.56
    Activations Density 2.655%

    No Known Activations