© 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. 17210
    Prev
    Next
    INDEX
    Explanations

    references to salt and its implications in various contexts

    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
     وتسجيلات
    -1.04
    ,:);
    -0.91
     McAllister
    -0.90
     للاسماء
    -0.90
     ujednoznacz
    -0.86
    řevě
    -0.86
     للمعارف
    -0.85
     تانيه
    -0.83
     Проци
    -0.80
    <<<<<<<<
    -0.79
    POSITIVE LOGITS
     Salt
    1.24
     salt
    1.15
    Salt
    1.12
    salt
    0.98
    Hart
    0.95
     Hart
    0.92
     SALT
    0.85
     salts
    0.79
     HART
    0.76
    SALT
    0.72
    Activations Density 0.004%

    No Known Activations