© 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. 18-RES-MATRYOSHKA-DC
    7. 452
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health, both mental and physical

    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.18.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.18.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
    AsUp
    -0.92
    bbene
    -0.90
     AssemblyCulture
    -0.89
     réguli
    -0.81
     Roskov
    -0.73
     quæ
    -0.72
     feroit
    -0.70
    protoimpl
    -0.70
    ThroughAttribute
    -0.66
     épaules
    -0.66
    POSITIVE LOGITS
    ized
    0.80
     gezien
    0.70
    ALLY
    0.69
    上的
    0.67
    ization
    0.63
    idal
    0.63
    ally
    0.61
    '])
    0.59
    रण
    0.59
     olarak
    0.58
    Activations Density 3.030%

    No Known Activations