© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3919
    Prev
    Next
    INDEX
    Explanations

    conclusive statements and ultimate outcomes in discussions or analyses

    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
     nakalista
    -0.80
    
    -0.76
     AssemblyCompany
    -0.73
    OrBuilder
    -0.72
    verwijspagina
    -0.71
     JpaRepository
    -0.68
    endedor
    -0.65
    rungsseite
    -0.63
    saraba
    -0.63
    AddTagHelper
    -0.63
    POSITIVE LOGITS
    Ultimately
    1.27
     Ultimately
    1.17
     ultimately
    1.10
     uiteindelijk
    1.05
    Eventually
    0.93
     Eventually
    0.93
     eventually
    0.88
    ulti
    0.87
     ultimate
    0.87
    eventually
    0.87
    Activations Density 0.136%

    No Known Activations