© 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. 11877
    Prev
    Next
    INDEX
    Explanations

    strong emphasis or highlighted points in a document

    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
    NOST
    -0.48
    শে
    -0.46
     Evidently
    -0.43
     StatefulWidget
    -0.42
     jspb
    -0.42
    berto
    -0.42
     Overs
    -0.42
     privatisation
    -0.41
    NOPQRST
    -0.41
    almaz
    -0.41
    POSITIVE LOGITS
     estekak
    0.70
     الحره
    0.70
    RegressionTest
    0.68
    ,:]
    0.68
    NameInMap
    0.66
    تقاوى
    0.66
     Seeder
    0.64
    PerformLayout
    0.62
    OrNil
    0.62
    }$}
    0.61
    Activations Density 0.001%

    No Known Activations