© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8885
    Prev
    Next
    INDEX
    Explanations

    references to figures or diagrams in technical documents

    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
    "])
    -0.84
    }))
    -0.76
     NDL
    -0.75
    mybatisplus
    -0.72
    makeConstraints
    -0.71
     فريبيس
    -0.68
    ukone
    -0.68
    )}
    -0.67
    esgue
    -0.67
     estekak
    -0.66
    POSITIVE LOGITS
     FIG
    1.16
    FIG
    0.97
     مشين
    0.66
     riservata
    0.64
    sepeda
    0.63
     Geos
    0.61
     eccell
    0.61
     titolata
    0.60
     väx
    0.60
    ورده
    0.57
    Activations Density 0.006%

    No Known Activations