© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    references to phase shifts and relationships in quantum or electromagnetic contexts

    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
     angles
    -0.59
     mesti
    -0.55
     Angles
    -0.55
     katze
    -0.54
     gratuitement
    -0.52
    AMAZ
    -0.52
    Gazette
    -0.52
     pageSize
    -0.52
     Toro
    -0.52
    wechsel
    -0.52
    POSITIVE LOGITS
    ductory
    0.68
    abestanden
    0.67
    GEBURTSDATUM
    0.66
    ObjectContext
    0.65
     noDo
    0.62
     Roskov
    0.62
    onViewCreated
    0.59
    ruptedException
    0.59
    UnusedPrivate
    0.57
    XmlAccessType
    0.56
    Activations Density 0.018%

    No Known Activations