© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5570
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "ful" indicating a focus on the concept of 'fullness' or something described as 'full'

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تفصیلات
    -0.69
     חיצוניים
    -0.69
    DotNetBar
    -0.60
    IonicModule
    -0.58
    ]));
    -0.57
    PreferredItem
    -0.57
    dafx
    -0.56
    +#+#
    -0.56
    assertAll
    -0.56
    oneofs
    -0.56
    POSITIVE LOGITS
    ful
    3.69
    FUL
    3.03
    fulness
    2.67
    fully
    2.59
    Ful
    2.11
    fuls
    2.11
    FULLY
    1.90
     ful
    1.76
    full
    1.72
     Ful
    1.58
    Activations Density 0.006%

    No Known Activations