© 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. 32481
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gain," indicating a focus on acquiring or increasing something

    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
    ordnung
    -0.64
     McDon
    -0.62
     Schlacht
    -0.61
     Corcoran
    -0.61
    dorp
    -0.59
     Cindy
    -0.59
     Brown
    -0.58
     Fred
    -0.58
    ئيس
    -0.57
     samo
    -0.57
    POSITIVE LOGITS
     GAIN
    1.28
     Gains
    1.19
    gain
    1.18
     Gain
    1.13
    Gain
    1.09
     gains
    1.07
    gains
    1.07
     gain
    1.05
     gained
    0.98
    GAIN
    0.98
    Activations Density 0.014%

    No Known Activations