© 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. 26947
    Prev
    Next
    INDEX
    Explanations

    phrases related to speaking, reporting, or conveying information

    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
     OnInit
    -0.65
     CreateTagHelper
    -0.61
     RSSSF
    -0.52
     referee
    -0.49
    getActiveSheet
    -0.49
     reafon
    -0.49
     Arp
    -0.48
    HtmlAttribute
    -0.47
    ichtlich
    -0.47
     reaſon
    -0.47
    POSITIVE LOGITS
    новништво
    0.70
    Referanser
    0.65
    principalColumn
    0.65
     AssemblyProduct
    0.63
    SpringBootTest
    0.61
    Hochspringen
    0.59
    
    0.59
     JpaRepository
    0.59
    __':
    0.58
     &___
    0.56
    Activations Density 0.204%

    No Known Activations