© 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. 14535
    Prev
    Next
    INDEX
    Explanations

    variations of the contraction "it's" or "it's" usage in different 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
    })]
    -0.99
    ')"
    -0.91
     برانيه
    -0.91
     Shee
    -0.91
     Nicky
    -0.85
    ộp
    -0.83
     déb
    -0.83
     NUKAT
    -0.83
    NameInMap
    -0.83
     دیکھیے
    -0.82
    POSITIVE LOGITS
    er
    1.11
     „
    0.68
    ´
    0.68
    erà
    0.68
     vuel
    0.67
     Snyder
    0.67
     Durant
    0.66
     Calder
    0.66
    le
    0.65
    zanie
    0.65
    Activations Density 0.021%

    No Known Activations