© 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. 25975
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnoses and sensory experiences

    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
    mosa
    -0.54
     pneumonia
    -0.52
    croll
    -0.52
    AnchorStyles
    -0.51
    oprecipitation
    -0.50
    راسیون
    -0.50
    énario
    -0.50
    pyplot
    -0.50
     drawn
    -0.48
     diarrhoea
    -0.48
    POSITIVE LOGITS
     sensation
    0.85
     sensations
    0.77
     Sensation
    0.74
    RegressionTest
    0.67
     TextInputType
    0.62
     Numb
    0.61
     sensación
    0.59
    sensory
    0.59
     sensazione
    0.58
     painless
    0.58
    Activations Density 0.054%

    No Known Activations