© 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. 10363
    Prev
    Next
    INDEX
    Explanations

    technical processes and terms related to production and efficiency

    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
    DeleteBehavior
    -0.82
     linkovi
    -0.79
    ExecuteReader
    -0.78
    XmlAccessType
    -0.69
    arote
    -0.66
    Parcelize
    -0.65
     חיצוניים
    -0.63
    MENAFN
    -0.62
    contentLoaded
    -0.61
     setAddress
    -0.60
    POSITIVE LOGITS
    abestanden
    0.47
     very
    0.43
     lần
    0.43
    +#+#
    0.42
    praš
    0.41
     lahat
    0.40
    govor
    0.39
     jeweiligen
    0.39
     rất
    0.39
     Both
    0.39
    Activations Density 0.131%

    No Known Activations