© 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. 5361
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to physical appearances and emotions

    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
    يدة
    -0.56
    MethodManager
    -0.54
     kiv
    -0.52
    stande
    -0.52
    Hentet
    -0.52
    ことがある
    -0.51
     personnal
    -0.50
    ਘ
    -0.49
     brother
    -0.49
     traditionally
    -0.49
    POSITIVE LOGITS
    +:+
    0.72
     utafitiHapana
    0.72
    writeFieldEnd
    0.66
     disambiguazione
    0.64
     Rimini
    0.64
    HasAnnotation
    0.64
     مرئيه
    0.63
     Numerade
    0.63
    QMetaType
    0.60
     ActionListener
    0.60
    Activations Density 0.287%

    No Known Activations