© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5396
    Prev
    Next
    INDEX
    Explanations

    numerical data and comparisons related to features or characteristics

    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
     للمعارف
    -0.97
    tvguidetime
    -0.93
     ProtoMessage
    -0.93
     snippetHide
    -0.93
     مشين
    -0.91
     فريبيس
    -0.90
     AssemblyTitle
    -0.81
    RuleContext
    -0.81
    Obrázky
    -0.77
     kasarigan
    -0.76
    POSITIVE LOGITS
     formed
    0.46
     base
    0.46
     Paglinawan
    0.46
     eventual
    0.45
     Donahue
    0.45
     eventually
    0.44
     open
    0.44
     autor
    0.44
    mäßige
    0.42
    箭头
    0.41
    Activations Density 0.449%

    No Known Activations