© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20953
    Prev
    Next
    INDEX
    Explanations

    references to hospital admissions and patient assessments

    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
    DockStyle
    -0.65
     Majefty
    -0.64
    PhysRevLett
    -0.63
     didel
    -0.60
     estekak
    -0.59
    setVerticalGroup
    -0.57
     дописавши
    -0.56
     purpoſe
    -0.56
    mybatisplus
    -0.56
    DataMember
    -0.55
    POSITIVE LOGITS
    OGND
    0.53
    Patron
    0.48
    tagHelperRunner
    0.47
     obicei
    0.47
    /***/
    0.45
    клопе
    0.45
    StoryboardSegue
    0.43
     Beratung
    0.42
     ItemStack
    0.42
    cèse
    0.42
    Activations Density 0.062%

    No Known Activations