© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25586
    Prev
    Next
    INDEX
    Explanations

    references to complex themes in literature, particularly involving relationships and narrative structure

    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
     car
    -0.44
    Tributes
    -0.43
    ävät
    -0.42
    Personendaten
    -0.42
     views
    -0.41
    rdom
    -0.41
     membership
    -0.41
     phá
    -0.41
     kaplama
    -0.40
     عامة
    -0.40
    POSITIVE LOGITS
    expandindo
    1.10
     kasarigan
    0.99
     EClass
    0.92
    تقاوى
    0.78
    SourceChecksum
    0.78
    NameInMap
    0.72
     Wikimedijinoj
    0.71
    UnsafeEnabled
    0.71
    UnknownFieldSet
    0.69
    AndroidJUnit
    0.68
    Activations Density 0.023%

    No Known Activations