© 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. 11277
    Prev
    Next
    INDEX
    Explanations

    statements related to expectations in coding tests

    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
     Ribera
    -0.76
     Lombar
    -0.69
     Medellín
    -0.68
    mallows
    -0.65
     Frédéric
    -0.61
     accelerators
    -0.61
     PSM
    -0.60
    ednes
    -0.59
    ۜ
    -0.58
    encers
    -0.57
    POSITIVE LOGITS
    ]-->
    0.67
     estimés
    0.66
     فريبيس
    0.65
    abstractmethod
    0.65
     StatefulWidget
    0.63
    setattr
    0.61
     otomatig
    0.59
     ArrayAdapter
    0.59
    DriverManager
    0.59
    DBNull
    0.59
    Activations Density 0.012%

    No Known Activations