© 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. 253
    Prev
    Next
    INDEX
    Explanations

    words and phrases that intensify or enhance other positive qualities

    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
     ModelExpression
    -0.98
    出版年
    -0.88
     CreateTagHelper
    -0.86
     незавершена
    -0.83
     perfons
    -0.83
     étoit
    -0.83
    bootstrapcdn
    -0.81
    новниш
    -0.80
    WriteBarrier
    -0.80
     Majefty
    -0.77
    POSITIVE LOGITS
     productive
    0.71
     informative
    0.69
     efficient
    0.65
     impactful
    0.63
     engaging
    0.60
     enjoyable
    0.59
     satisfying
    0.59
     rewarding
    0.57
     communicative
    0.57
     effective
    0.57
    Activations Density 1.918%

    No Known Activations