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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 458
    Prev
    Next
    INDEX
    Explanations

    statistical terms related to analysis and outcomes in research data

    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
    <eos>
    -0.63
     and
    -0.58
     an
    -0.55
     a
    -0.53
     "
    -0.47
     or
    -0.47
    ,
    -0.47
     the
    -0.44
    2
    -0.44
    .
    -0.44
    POSITIVE LOGITS
    awtextra
    1.27
     <>",
    1.23
     Efq
    1.20
    ConstraintMaker
    1.17
     ModelExpression
    1.11
     للاسماء
    1.10
     تضيفلها
    1.09
    complexContent
    1.05
     مشين
    1.05
    Personensuche
    1.05
    Activations Density 1.803%

    No Known Activations