© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16144
    Prev
    Next
    INDEX
    Explanations

    scientific analyses and evaluations related to experimental methods and results

    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
    ()?;
    -0.60
    lish
    -0.52
    form
    -0.49
    ără
    -0.49
    []>(
    -0.49
    }(),
    -0.48
    allow
    -0.47
     Arrondissement
    -0.47
    %'
    -0.47
     hObject
    -0.46
    POSITIVE LOGITS
    ChildScrollView
    0.77
     BoxDecoration
    0.72
    ponses
    0.71
    脚注の使い方
    0.70
    makeText
    0.68
     للمعارف
    0.67
     <<<<<<<<<<<<<<
    0.63
    viewDidLoad
    0.63
     clearColor
    0.62
     trạng
    0.61
    Activations Density 0.046%

    No Known Activations