© 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. 23599
    Prev
    Next
    INDEX
    Explanations

    references to press-related activities and media communication

    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
     thế
    -0.52
     scor
    -0.50
     dend
    -0.50
     poema
    -0.49
    dend
    -0.48
     app
    -0.47
    ersch
    -0.45
    toe
    -0.45
    vartheta
    -0.45
    стви
    -0.45
    POSITIVE LOGITS
     NSCoder
    0.89
    uxxxx
    0.83
    Personensuche
    0.81
     imprensa
    0.79
     ddelweddau
    0.79
    ftagPool
    0.79
     FetchType
    0.78
     Presse
    0.74
    jsonwebtoken
    0.73
    ValueStyle
    0.69
    Activations Density 0.028%

    No Known Activations