© 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. 24-RES-MATRYOSHKA-DC
    7. 266
    Prev
    Next
    INDEX
    Explanations

    words that appear in research-style documents, where some investigation is performed and the results are needed for a particular purpose

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    aarrggbb
    -0.69
    到
    -0.65
    gonic
    -0.52
    KommentareTeilen
    -0.51
    InitStruct
    -0.50
    AndEndTag
    -0.50
    from
    -0.50
    astéro
    -0.48
    到你
    -0.48
     Administrativna
    -0.48
    POSITIVE LOGITS
     for
    3.17
     для
    1.75
    for
    1.73
     für
    1.61
     untuk
    1.59
     voor
    1.52
    สำหรับ
    1.51
     برای
    1.48
     για
    1.44
     pentru
    1.38
    Activations Density 6.688%

    No Known Activations