© 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. 20745
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transitions or changes in state

    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
     however
    -0.51
     SQLAlchemy
    -0.49
     traceback
    -0.48
     BIB
    -0.47
    Dade
    -0.47
     Всё
    -0.47
     Tus
    -0.46
    Fallout
    -0.46
     Ponta
    -0.46
    ppus
    -0.45
    POSITIVE LOGITS
    قایناق‌لار
    0.87
    OrBuilder
    0.83
     prisonniers
    0.81
    NUMX
    0.77
     Larson
    0.76
    rungsseite
    0.75
     côtes
    0.73
    bitField
    0.73
    原始内容存档于
    0.72
    GEBURTSDATUM
    0.72
    Activations Density 0.009%

    No Known Activations