© 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. 6-RES-MATRYOSHKA-DC
    7. 1076
    Prev
    Next
    INDEX
    Explanations

    the word "than" followed by various pronouns or nouns

    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
     ostavi
    -0.95
    脚注の使い方
    -0.88
    GetKeyDown
    -0.82
     يتيمه
    -0.82
    JoinColumn
    -0.80
    Tikang
    -0.77
    FailureListener
    -0.77
     BoxDecoration
    -0.76
     Polisi
    -0.76
    География
    -0.74
    POSITIVE LOGITS
     THAN
    1.90
     than
    1.85
     Than
    1.60
    Than
    1.55
    than
    1.42
    THAN
    1.37
     než
    1.16
     ніж
    1.14
     niż
    1.09
     än
    1.04
    Activations Density 0.403%

    No Known Activations