© 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. 20006
    Prev
    Next
    INDEX
    Explanations

    specific instances or occurrences that are labeled "given" in the context of particular conditions or situations

    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
     all
    -0.66
     autorytatywna
    -0.65
    Entrée
    -0.56
     lặng
    -0.55
    مصادر
    -0.54
     pages
    -0.54
    alih
    -0.54
     patas
    -0.54
    HERO
    -0.54
     Fun
    -0.53
    POSITIVE LOGITS
    RunWith
    0.78
    WaitGroup
    0.78
    ConverterFactory
    0.70
    ArgsConstructor
    0.69
     الرياضيه
    0.67
    ſelf
    0.66
    yntaxException
    0.65
     estekak
    0.64
     تضيفلها
    0.62
    ngrx
    0.62
    Activations Density 0.009%

    No Known Activations