© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    mentions of health-related issues

    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
     dikenal
    -0.75
     known
    -0.73
    Known
    -0.72
     Known
    -0.71
    AttributeSet
    -0.70
    known
    -0.68
    WireFormatLite
    -0.66
     Considered
    -0.65
    хьтан
    -0.64
     regarded
    -0.63
    POSITIVE LOGITS
     common
    1.37
    common
    1.25
     Common
    1.05
     communs
    1.05
     comunes
    1.03
     frequent
    1.01
     COMMON
    0.99
    Common
    0.97
    COMMON
    0.96
     comuns
    0.96
    Activations Density 0.219%

    No Known Activations