© 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. 24-RES-MATRYOSHKA-DC
    7. 496
    Prev
    Next
    INDEX
    Explanations

    medical research related words and phrases

    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.24.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.24.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
    IntoConstraints
    -0.68
    crollView
    -0.57
    ISupport
    -0.57
    MigrationBuilder
    -0.55
    plasia
    -0.52
    κτηρισ
    -0.52
    perity
    -0.52
    AIRS
    -0.51
    árl
    -0.50
     tunn
    -0.50
    POSITIVE LOGITS
     therapy
    1.09
     administration
    1.01
     administered
    0.96
     treatment
    0.93
     therapies
    0.93
     therapeutic
    0.91
     drugs
    0.89
    administration
    0.88
     Therapy
    0.87
     drug
    0.86
    Activations Density 4.062%

    No Known Activations