© 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. 11728
    Prev
    Next
    INDEX
    Explanations

    references to mountains

    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
    enumi
    -0.84
    ocino
    -0.83
    SpringBootTest
    -0.79
    новниш
    -0.78
     ujednoznacz
    -0.76
     arşivlendi
    -0.75
     Redux
    -0.75
    lucene
    -0.75
    oriasis
    -0.74
    moiselle
    -0.74
    POSITIVE LOGITS
     Mountain
    1.61
     mountain
    1.45
    Mountain
    1.42
     MOUNTAIN
    1.29
     mountains
    1.27
    mountain
    1.23
     Moun
    1.15
     Mountains
    1.13
     moun
    1.09
    ountain
    1.06
    Activations Density 0.008%

    No Known Activations