© 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. 2-RES-MATRYOSHKA-DC
    7. 7483
    Prev
    Next
    INDEX
    Explanations

    entries related to scientific publications and patent documentation

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ⓘ
    -0.69
    DebuggerStep
    -0.68
    /***/
    -0.60
    "?>
    -0.60
    kijken
    -0.59
    Demografía
    -0.57
    PageModule
    -0.56
    rawDesc
    -0.56
    })));
    -0.55
    BeginInit
    -0.54
    POSITIVE LOGITS
     transférez
    0.59
     betweenstory
    0.59
     transfieras
    0.57
    Демографія
    0.54
    ArrowToggle
    0.53
    +#+#
    0.52
    Rüyada
    0.50
     '\\;'
    0.50
    postsleuth
    0.47
    TypedDataSet
    0.46
    Activations Density 0.232%

    No Known Activations