© 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. 32383
    Prev
    Next
    INDEX
    Explanations

    numerical data, specifically focusing on various counting figures or values associated with performance in different 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
    Negative Logits
    raits
    -0.68
    MENAFN
    -0.66
    ThroughAttribute
    -0.65
    LookAnd
    -0.64
    NOPQRST
    -0.61
    PRNewswire
    -0.60
     moth
    -0.60
     TestBed
    -0.60
    providedIn
    -0.60
    المكان
    -0.59
    POSITIVE LOGITS
     EClass
    0.48
    тистика
    0.46
     estekak
    0.46
     frame
    0.45
    gående
    0.43
     year
    0.42
     AssemblyCulture
    0.41
    Viitteet
    0.41
     tiefer
    0.40
    RenderAtEndOf
    0.40
    Activations Density 0.037%

    No Known Activations