© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5632
    Prev
    Next
    INDEX
    Explanations

    terminology related to medical conditions and their diagnoses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Cyfeiriadau
    -0.73
    DataAnnotations
    -0.63
     Normdatei
    -0.62
     VIDEOTAPE
    -0.59
    EndContext
    -0.57
    azgo
    -0.57
     taban
    -0.57
     Ráp
    -0.56
    ScopeManager
    -0.56
    IsContent
    -0.55
    POSITIVE LOGITS
    发表于
    0.56
    toler
    0.56
     发表于
    0.54
     Mild
    0.53
     harmless
    0.53
     biasa
    0.52
     rather
    0.52
     mildly
    0.52
     everyday
    0.51
     minor
    0.51
    Activations Density 1.284%

    No Known Activations