© 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. 24563
    Prev
    Next
    INDEX
    Explanations

    the presence of underscores in a structured format

    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
    InjectAttribute
    -0.83
    ?";
    -0.72
    />";
    -0.71
    horabuena
    -0.71
     MÁ
    -0.64
     tslint
    -0.63
     themſelves
    -0.62
    SequentialGroup
    -0.61
     HasFactory
    -0.60
     שוליים
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.78
    Mitglieder
    0.63
    remel
    0.63
    vallis
    0.63
    laceae
    0.61
    benhavn
    0.60
     Picchu
    0.60
    ValueStyle
    0.59
     Landis
    0.58
     Scotia
    0.57
    Activations Density 0.008%

    No Known Activations