© 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. 3-RES-MATRYOSHKA-DC
    7. 191
    Prev
    Next
    INDEX
    Explanations

    a mix of words from medical, vehicles and chemistry/technical domains

    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
    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
    konomi
    -0.63
    amını
    -0.62
     مرئيه
    -0.59
    skrift
    -0.59
    agascar
    -0.58
     indisponible
    -0.58
    ACEAE
    -0.57
     تانيه
    -0.57
    міст
    -0.56
    benhavn
    -0.55
    POSITIVE LOGITS
    withstanding
    0.78
    ยว
    0.77
    CrossRef
    0.74
    -${
    0.72
    +#+#
    0.72
    lapsingToolbar
    0.71
     itſelf
    0.68
    RTLD
    0.66
    -/**
    0.64
    Rptr
    0.62
    Activations Density 4.888%

    No Known Activations