© 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. 2250
    Prev
    Next
    INDEX
    Explanations

    the word "the" especially when near the beginning of a sentence or in a title

    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
    LookAnd
    -0.82
    tvguidetime
    -0.81
    المناصب
    -0.80
    
    -0.79
    PerformLayout
    -0.70
     EconPapers
    -0.69
    adpleegd
    -0.65
    nesty
    -0.65
    exels
    -0.65
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
     how
    0.78
    how
    0.68
    what
    0.55
     cómo
    0.53
     what
    0.53
    How
    0.51
    cómo
    0.50
    OGND
    0.48
    }{*}{}
    0.48
    PrototypeOf
    0.48
    Activations Density 0.597%

    No Known Activations