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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13563
    Prev
    Next
    INDEX
    Explanations

    the mention of the technique "crystal holography" or related crystal structure techniques

    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
    expandindo
    -0.74
    RunWith
    -0.74
    imetsu
    -0.64
    difice
    -0.60
    :✨
    -0.57
    nestjs
    -0.57
    сылкі
    -0.56
    فحة
    -0.56
    atru
    -0.56
    Datuak
    -0.55
    POSITIVE LOGITS
    lographic
    3.06
    lography
    2.84
    lograph
    2.56
     holographic
    1.76
    logram
    1.55
     holog
    1.13
     hologram
    1.03
    NOPQRST
    0.64
     مرئيه
    0.59
    ++]=
    0.54
    Activations Density 0.001%

    No Known Activations