© 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. 855
    Prev
    Next
    INDEX
    Explanations

    words related to skin conditions and medical treatments

    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
    anadium
    -0.74
     propOrder
    -0.70
    ocarditis
    -0.70
    KURZBESCHREIBUNG
    -0.64
    lapsingToolbar
    -0.63
    IntoConstraints
    -0.62
     estekak
    -0.62
    RoutingModule
    -0.60
    TagMode
    -0.59
     mitral
    -0.59
    POSITIVE LOGITS
     skin
    1.65
     Skin
    1.45
    Skin
    1.38
    skin
    1.33
     SKIN
    1.18
     dermat
    1.17
     Dermat
    1.15
     dermatologist
    1.15
     skins
    1.13
     peau
    1.06
    Activations Density 0.892%

    No Known Activations