© 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. 15530
    Prev
    Next
    INDEX
    Explanations

    phrases indicating perception or observation

    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
    elsen
    -0.60
     Saw
    -0.60
    出版年
    -0.58
    xticks
    -0.58
     JSTOR
    -0.57
     Jacobsen
    -0.57
     SITES
    -0.57
    Wong
    -0.57
     Borgo
    -0.57
     lccn
    -0.57
    POSITIVE LOGITS
    ftagPool
    0.96
     فريبيس
    0.73
     <=",
    0.66
    IsContent
    0.65
    RectangleBorder
    0.65
    BASEPATH
    0.65
    Datuak
    0.62
    MockBean
    0.62
    مراجع
    0.61
     Carlisle
    0.61
    Activations Density 0.034%

    No Known Activations