© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14085
    Prev
    Next
    INDEX
    Explanations

    references to the geometric shape "square" and its associated numerical attributes

    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
    WriteAttribute
    -0.76
    InputBorder
    -0.76
    +#+#
    -0.71
    AddTagHelper
    -0.70
    SizeF
    -0.70
    下载附件
    -0.66
    fillType
    -0.65
    AnchorStyles
    -0.62
     كره
    -0.61
    âneo
    -0.60
    POSITIVE LOGITS
    square
    1.85
    □
    0.79
     OMITBAD
    0.59
     □
    0.57
     Seeder
    0.54
    SQUARE
    0.54
    ynx
    0.52
    toPromise
    0.51
    Билгалдахарш
    0.50
    dalena
    0.50
    Activations Density 0.001%

    No Known Activations