© 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. 839
    Prev
    Next
    INDEX
    Explanations

    the word `close` and its variants, particularly with reference to doors or abstract theoretical constructs like equations

    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
     AssemblyProduct
    -1.00
     CreateTagHelper
    -0.86
    AppMethodBeat
    -0.85
    QMetaType
    -0.82
    IsMutable
    -0.80
    WireFormatLite
    -0.77
     Cavendish
    -0.77
    GOTREF
    -0.76
    multer
    -0.74
     modelAndView
    -0.73
    POSITIVE LOGITS
     closed
    2.02
     closes
    1.88
     closing
    1.84
     Closed
    1.84
     clos
    1.79
    Closed
    1.77
     CLOS
    1.66
    closed
    1.65
     CLOSED
    1.63
     Closing
    1.62
    Activations Density 0.265%

    No Known Activations