© 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. 31039
    Prev
    Next
    INDEX
    Explanations

    variations of the word "choose."

    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
     sánchez
    -0.91
     lópez
    -0.84
     Entsche
    -0.80
     rodríguez
    -0.80
     noft
    -0.79
     parís
    -0.75
    Avi
    -0.74
     dentelle
    -0.74
     McDaniel
    -0.74
     Infantil
    -0.73
    POSITIVE LOGITS
    Hauptartikel
    0.85
     Thu
    0.82
    ://"
    0.81
    &=&\
    0.76
     %>
    0.73
    ✨:
    0.73
    fromCharCode
    0.73
     виправивши
    0.72
    "}")
    0.71
    metheus
    0.70
    Activations Density 0.015%

    No Known Activations