© 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. 22-RES-MATRYOSHKA-DC
    7. 2512
    Prev
    Next
    INDEX
    Explanations

    the phrase "prior art", or related words like "related prior"

    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.22.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.22.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
    enumii
    -0.68
    ChildScrollView
    -0.67
    帖最后由
    -0.66
    protoimpl
    -0.63
    例句
    -0.61
     LoggerFactory
    -0.61
    CodedInputStream
    -0.60
    Ủ
    -0.60
    ukone
    -0.57
    VersionUID
    -0.56
    POSITIVE LOGITS
     art
    2.45
    art
    1.97
    Art
    1.94
     Art
    1.93
     ART
    1.63
     arts
    1.59
    ART
    1.47
    arts
    1.40
     Kunst
    1.26
     Arts
    1.25
    Activations Density 0.057%

    No Known Activations