© 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. 23218
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between entities

    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
    jspx
    -0.55
    orghini
    -0.54
    NewUrlParser
    -0.53
     فريبيس
    -0.53
     tâche
    -0.51
    }`).
    -0.49
    ^*)
    -0.49
    ⤹
    -0.49
    </tfoot>
    -0.49
    </>
    -0.49
    POSITIVE LOGITS
     estekak
    0.73
     كومونز
    0.66
    Референце
    0.59
    日閲覧
    0.59
    GeneratedMessage
    0.58
    脚注の使い方
    0.56
    Зноскі
    0.54
    DoubleQuotes
    0.51
     ciutat
    0.50
     khảo
    0.49
    Activations Density 0.126%

    No Known Activations