© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    mentions of uncertainty or opinions regarding popular beliefs

    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
    ItemBackground
    -0.76
     Réponses
    -0.75
     Dider
    -0.65
    Aktualisiert
    -0.64
    kháu
    -0.64
    newArrayList
    -0.63
     للمعارف
    -0.61
    tdessen
    -0.61
    cendental
    -0.61
    λίου
    -0.60
    POSITIVE LOGITS
     zumindest
    0.64
    ंदीखरीदारी
    0.50
    BufferException
    0.50
     defaultstate
    0.50
     solange
    0.46
     tentativo
    0.45
     localObject
    0.45
    Nuorodos
    0.45
     certainly
    0.44
    indest
    0.44
    Activations Density 0.148%

    No Known Activations