© 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. 6498
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes in a JSON-like format

    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
     T
    -0.80
     
    -0.76
     p
    -0.72
     I
    -0.72
     The
    -0.70
     To
    -0.70
     In
    -0.69
     P
    -0.68
     N
    -0.67
     .
    -0.67
    POSITIVE LOGITS
     itſelf
    1.30
     myſelf
    1.28
     فريبيس
    1.22
    ValueStyle
    1.17
     doubtnut
    1.17
     Monfieur
    1.17
     themſelves
    1.12
     ་་
    1.12
     Roskov
    1.12
     Efq
    1.10
    Activations Density 0.139%

    No Known Activations