© 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. 26161
    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
    Not in Any Lists

    No Comments

    Negative Logits
     pageContext
    -0.54
     Aman
    -0.53
    ällor
    -0.53
     нет
    -0.52
     EnglishChoose
    -0.51
    ografija
    -0.50
    taient
    -0.50
     goûts
    -0.49
     Careful
    -0.49
     хвати
    -0.48
    POSITIVE LOGITS
     GenerationType
    0.86
    ynchronously
    0.70
    phrag
    0.66
     CanadaChoose
    0.66
     تضيفلها
    0.65
    withIdentifier
    0.65
     cref
    0.64
    getDoctrine
    0.63
    VersionUID
    0.62
    ]**
    0.61
    Activations Density 0.019%

    No Known Activations