© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    terms associated with immune status and health conditions

    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
    setVerticalGroup
    -0.77
     betweenstory
    -0.69
    
    -0.67
    Vanjske
    -0.64
    fjspx
    -0.62
    KELEY
    -0.61
     EconPapers
    -0.61
    tvguidetime
    -0.61
    yntaxException
    -0.59
     kasarigan
    -0.59
    POSITIVE LOGITS
     vulnerable
    0.46
     />,
    0.45
     weakened
    0.44
    writeHead
    0.42
    oporosis
    0.41
    ffine
    0.40
    UniformLocation
    0.38
    }):
    0.38
     осла
    0.38
    userdetails
    0.38
    Activations Density 0.049%

    No Known Activations