© 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. 22-RES-MATRYOSHKA-DC
    7. 3095
    Prev
    Next
    INDEX
    Explanations

    the first person "I" along with auxiliary verbs and prepositions that usually follow it.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     ComVisible
    -0.79
     transférez
    -0.65
     שוליים
    -0.63
    InjectAttribute
    -0.59
     وتسجيلات
    -0.58
     surla
    -0.57
    transQ
    -0.57
    enterOuterAlt
    -0.57
    TargetException
    -0.57
    ErrUnexpectedEOF
    -0.56
    POSITIVE LOGITS
     doing
    2.72
     do
    2.58
    Doing
    2.47
     Doing
    2.44
    doing
    2.28
     did
    2.09
    do
    2.08
     does
    1.98
     done
    1.98
     DOING
    1.98
    Activations Density 1.230%

    No Known Activations