© 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. 10519
    Prev
    Next
    INDEX
    Explanations

    the word "or."

    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
    jface
    -0.63
    alised
    -0.60
    Busch
    -0.59
     Busch
    -0.57
    undred
    -0.56
    ſand
    -0.54
    stdarg
    -0.54
    lised
    -0.52
    solicitud
    -0.52
     تعد
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.83
     Meksiku
    0.69
    netbeans
    0.63
    الإنجليزية
    0.62
    IntoConstraints
    0.62
     ModelExpression
    0.59
    Personendaten
    0.58
    atilde
    0.57
    تقاوى
    0.56
     certiorari
    0.56
    Activations Density 0.002%

    No Known Activations