© 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
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 486
    Prev
    Next
    INDEX
    Explanations

    the verb "make" and city names or words starting with "your"

    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
     htons
    -0.93
    GenerationType
    -0.85
     comigo
    -0.84
     titolata
    -0.83
     Roskov
    -0.82
     verrou
    -0.80
    LEGGI
    -0.79
    endpush
    -0.79
    tagext
    -0.79
    ContentAlignment
    -0.79
    POSITIVE LOGITS
     made
    2.73
    make
    2.63
    made
    2.58
     make
    2.56
    Make
    2.52
    Made
    2.47
     Make
    2.45
     MADE
    2.42
     Made
    2.39
     MAKE
    2.39
    Activations Density 0.898%

    No Known Activations