© 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. 25520
    Prev
    Next
    INDEX
    Explanations

    the word "which" 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
    who
    -0.72
    Whose
    -0.70
    sizeCache
    -0.69
    脚注の使い方
    -0.67
     whose
    -0.66
    LookAnd
    -0.66
     Whose
    -0.65
    whose
    -0.65
     cuyas
    -0.65
    Jeografia
    -0.64
    POSITIVE LOGITS
     handleMessage
    0.59
    altes
    0.55
    felf
    0.54
    igram
    0.54
    úsqueda
    0.52
    PopUp
    0.51
    템
    0.48
    isValid
    0.47
     tuya
    0.47
    ruvate
    0.47
    Activations Density 0.055%

    No Known Activations