© 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. 30191
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and treatment outcomes

    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
    ."],
    -0.90
    ########.
    -0.88
     Efq
    -0.86
    MLLoader
    -0.85
     }}$}
    -0.81
     faſt
    -0.80
    StructEnd
    -0.79
     مرئيه
    -0.77
    oa̍t
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
    .
    0.45
      
    0.43
    esto
    0.41
     on
    0.40
    来る
    0.40
    on
    0.39
     
    0.39
    <strong>
    0.39
     how
    0.38
    oucí
    0.38
    Activations Density 0.023%

    No Known Activations