© 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. 0-RES-MATRYOSHKA-DC
    7. 13138
    Prev
    Next
    INDEX
    Explanations

    the presence of "double-sided" indicating a focus on objects or items characterized by being double-sided

    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
    iding
    -2.53
    ided
    -1.96
    idings
    -0.98
    IDING
    -0.90
    aided
    -0.73
     aided
    -0.67
     arşivlendi
    -0.65
     aidé
    -0.64
     siding
    -0.63
    ision
    -0.59
    POSITIVE LOGITS
    sided
    1.38
    Насе
    0.53
    ستار
    0.51
    vignon
    0.51
    aarrggbb
    0.50
     الحره
    0.50
     trattano
    0.47
    CJK
    0.47
    Nguồn
    0.47
    engelsk
    0.47
    Activations Density 0.000%

    No Known Activations