© 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. 11636
    Prev
    Next
    INDEX
    Explanations

    numerical data related to patient samples and their analysis outcomes

    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
    hythm
    -0.63
     True
    -0.54
     nat
    -0.53
     le
    -0.52
    emang
    -0.52
     land
    -0.50
     ci
    -0.48
     care
    -0.48
     task
    -0.48
     】
    -0.48
    POSITIVE LOGITS
     defStyleAttr
    0.88
    ChildScrollView
    0.87
    seamnă
    0.80
     '\\;'
    0.73
     picioare
    0.73
     rând
    0.71
     prieten
    0.70
     gând
    0.70
    GraphicsUnit
    0.69
    writeField
    0.69
    Activations Density 0.062%

    No Known Activations