© 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. 15932
    Prev
    Next
    INDEX
    Explanations

    references to gene mutations, particularly those associated with *KRAS* related conditions

    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
    Negative Logits
    zboi
    -0.75
     Jock
    -0.73
     tratti
    -0.71
    k
    -0.71
    ⓘ
    -0.70
     spørsmål
    -0.68
     Farah
    -0.67
    AW
    -0.66
     età
    -0.65
    ATR
    -0.64
    POSITIVE LOGITS
    "):
    0.96
     LCD
    0.94
    )");
    0.88
     Jefferson
    0.88
     Kr
    0.86
     Krü
    0.84
    LCD
    0.84
     krzy
    0.83
     lcd
    0.79
     <<<<<<<<<<<<<<
    0.79
    Activations Density 0.040%

    No Known Activations