© 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. 2279
    Prev
    Next
    INDEX
    Explanations

    the suffix "inal" or "ial" in the context of neuroscience and anatomy

    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
    josh
    -0.75
    LLS
    -0.67
    LOC
    -0.66
     getRule
    -0.65
     LOC
    -0.63
     physic
    -0.60
    ayn
    -0.59
    cologist
    -0.59
    Хро
    -0.59
    TRC
    -0.58
    POSITIVE LOGITS
    ial
    2.02
    inal
    1.72
    IAL
    1.65
    INAL
    1.49
    rial
    1.46
    ural
    1.38
    ional
    1.33
    tial
    1.27
    ital
    1.24
    minal
    1.18
    Activations Density 0.106%

    No Known Activations