© 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. 2-RES-MATRYOSHKA-DC
    7. 4217
    Prev
    Next
    INDEX
    Explanations

    references to fine particles or fine particle formation processes

    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
     Buena
    -0.67
    RTLR
    -0.66
     Drury
    -0.63
     '\\;'
    -0.63
     vincit
    -0.61
     Vesu
    -0.60
    Efficiency
    -0.59
     Pohl
    -0.59
    vatar
    -0.58
    muz
    -0.58
    POSITIVE LOGITS
     fine
    3.98
    fine
    3.81
    Fine
    3.77
     Fine
    3.55
     FINE
    3.34
    FINE
    3.11
     finer
    2.28
     fines
    2.16
    fines
    1.94
     Fines
    1.91
    Activations Density 0.038%

    No Known Activations