© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 360
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies and cancer treatment outcomes, particularly response and survival rates.

    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
     diagnosis
    -0.59
     diagnose
    -0.58
     diagnosed
    -0.57
     مواليد
    -0.57
     Diagnosis
    -0.56
    Affected
    -0.54
     diagnóstico
    -0.53
    Diagnosis
    -0.51
     diagnos
    -0.50
     Diagnose
    -0.49
    POSITIVE LOGITS
     survival
    0.73
     Survival
    0.71
    survival
    0.70
     trial
    0.70
    Efficacy
    0.70
     futility
    0.66
    efficacy
    0.66
     efficacy
    0.65
     Efficacy
    0.64
     safety
    0.64
    Activations Density 2.611%

    No Known Activations