© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 1330
    Prev
    Next
    INDEX
    Explanations

    the word "of"

    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
    Of
    -0.74
     Of
    -0.72
     thereof
    -0.71
    Datuak
    -0.66
    
    -0.66
     OF
    -0.66
    OfWork
    -0.63
    omock
    -0.58
    of
    -0.56
    memberof
    -0.56
    POSITIVE LOGITS
    --)
    
    0.64
    '):
    
    0.61
    StructEnd
    0.58
    ]='\
    0.56
    cokinetics
    0.55
    UnitTesting
    0.55
    ViewFeatures
    0.54
    TintMode
    0.52
    ficulties
    0.52
    ).
    
    0.52
    Activations Density 1.234%

    No Known Activations