© 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. 28404
    Prev
    Next
    INDEX
    Explanations

    specific verbs and phrases related to current implementations and systems in use

    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
    -0.75
     وتسجيلات
    -0.73
    KommentareTeilen
    -0.65
     كومونز
    -0.65
    出版年
    -0.64
     gyhoeddwyd
    -0.63
    jgl
    -0.63
     Савезне
    -0.62
    setPointSize
    -0.62
     Meksiku
    -0.61
    POSITIVE LOGITS
     current
    0.90
     existing
    0.88
     currently
    0.87
     Current
    0.80
    Current
    0.77
     CURRENT
    0.76
     Currently
    0.74
    Currently
    0.73
    current
    0.72
    currently
    0.69
    Activations Density 0.164%

    No Known Activations