© 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. 24335
    Prev
    Next
    INDEX
    Explanations

    specific dates or references to time periods

    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
     pinulongan
    -0.57
    +:+
    -0.56
     AssemblyCompany
    -0.50
     revenir
    -0.48
    Бахар
    -0.48
    kloped
    -0.46
    Попис
    -0.46
     interne
    -0.46
    illige
    -0.44
    resizingMask
    -0.43
    POSITIVE LOGITS
     كومونز
    0.68
     betweenstory
    0.66
     للمعارف
    0.64
     AttributeSet
    0.63
     Theſe
    0.63
    itinéraire
    0.60
       
    0.59
    ConfigureAwait
    0.58
    তথ্যসূত্র
    0.56
     reaſon
    0.55
    Activations Density 0.012%

    No Known Activations