© 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. 22-RES-MATRYOSHKA-DC
    7. 1587
    Prev
    Next
    INDEX
    Explanations

    words and phrases discussing demographic diversity

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     onCreateView
    -0.73
    rawDesc
    -0.62
     препратки
    -0.55
    HtmlAttribute
    -0.54
    ]}>
    -0.52
    });
    -0.52
     tartalomajánló
    -0.50
    lijkse
    -0.50
     externi
    -0.49
    atrième
    -0.48
    POSITIVE LOGITS
     type
    1.54
     types
    1.40
     genre
    1.25
     species
    1.17
    类型
    1.15
    type
    1.13
     nationality
    1.09
     category
    1.09
     tipo
    1.08
     jenis
    1.08
    Activations Density 3.442%

    No Known Activations