© 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. 18034
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or conditions connected to the word "with."

    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
     विश्वसनीयता
    -0.59
    assies
    -0.56
    ">//
    -0.55
    piri
    -0.53
    unknownFields
    -0.50
    őbb
    -0.50
    Guards
    -0.50
     Roost
    -0.50
    存于互联网档案馆
    -0.50
    Спасылкі
    -0.49
    POSITIVE LOGITS
    XmlAccessorType
    0.73
     MainAxisSize
    0.67
     useDispatch
    0.66
    ENDIAN
    0.66
    BeginContext
    0.65
     kuiten
    0.62
     purpoſe
    0.61
    awakeFromNib
    0.60
    coration
    0.59
     utafitiHapana
    0.59
    Activations Density 0.026%

    No Known Activations