© 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. 23857
    Prev
    Next
    INDEX
    Explanations

    references to various attributes or aspects related to RX, CO, and ALES terminology

    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
     ***!
    -0.98
     חיצוניים
    -0.91
    ///</
    -0.88
     дописавши
    -0.84
    __':
    -0.73
    cshtml
    -0.72
    :+:
    -0.70
    marvin
    -0.69
    دانشنامهٔ
    -0.69
    __":
    -0.68
    POSITIVE LOGITS
     coales
    1.34
    addContainerGap
    0.78
    OrWhiteSpace
    0.69
    aleza
    0.66
    ərbaycan
    0.64
     SIL
    0.63
    åter
    0.63
     Moisés
    0.60
     ἔ
    0.60
    cetype
    0.59
    Activations Density 0.001%

    No Known Activations