© 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. 12024
    Prev
    Next
    INDEX
    Explanations

    variations of numerical references, particularly sections or parts of documents

    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
    BeforeEach
    -0.46
     Partagez
    -0.44
     Bet
    -0.44
    karni
    -0.42
     pourtant
    -0.42
    *****
    -0.42
     ehe
    -0.42
     aislados
    -0.42
     loi
    -0.41
     gomma
    -0.41
    POSITIVE LOGITS
    expandindo
    1.02
     оригіналу
    0.88
    RegistryLite
    0.85
    enumii
    0.79
     للاسماء
    0.77
    GEBURTSDATUM
    0.77
     &___
    0.76
    تقاوى
    0.75
    LookAnd
    0.72
    enumi
    0.71
    Activations Density 0.003%

    No Known Activations