© 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. 9321
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or event

    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
    Negative Logits
     memoized
    -0.75
    IVEREF
    -0.69
    évaluateur
    -0.69
    Билгалдахарш
    -0.69
    WebElementEntity
    -0.68
     uintptr
    -0.67
     autorytatywna
    -0.66
     userManager
    -0.65
    InjectAttribute
    -0.65
     pageContext
    -0.65
    POSITIVE LOGITS
     oso
    0.47
    jov
    0.45
     Pristupljeno
    0.44
    LAX
    0.44
     text
    0.43
    tipo
    0.42
     mer
    0.42
    viate
    0.42
    autoconfigure
    0.42
    auk
    0.41
    Activations Density 0.000%

    No Known Activations