© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    structured data referencing experimental conditions and results, likely related to clinical trials

    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
     disponibilités
    -0.54
    。)
    -0.47
     UnityEngine
    -0.45
     automó
    -0.45
    }));
    -0.45
    omla
    -0.44
    }));
    -0.42
    fao
    -0.41
    ferm
    -0.41
    .",
    -0.41
    POSITIVE LOGITS
     ProtoMessage
    0.85
     ویکی‌پدیا
    0.84
     Efq
    0.82
     صوتيه
    0.79
     whoſe
    0.77
    GEBURTSDATUM
    0.77
     Theſe
    0.75
     fubject
    0.74
    InjectAttribute
    0.72
     defaultstate
    0.72
    Activations Density 0.013%

    No Known Activations