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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15207
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly related to statistics or measurements

    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
    脚注の使い方
    -1.01
    ειτουργ
    -0.94
    ьаж
    -0.85
     autorytatywna
    -0.84
    Datuak
    -0.83
     Meksiku
    -0.83
    InjectAttribute
    -0.80
     nonatomic
    -0.80
    QMetaType
    -0.80
     initComponents
    -0.80
    POSITIVE LOGITS
     ۲۰۰
    0.67
     Tremb
    0.61
     George
    0.57
     ma
    0.56
    Doug
    0.56
     
    0.56
     Doug
    0.54
    CGContext
    0.54
     of
    0.52
    üne
    0.52
    Activations Density 0.092%

    No Known Activations